© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 4884
    Prev
    Next
    INDEX
    Explanations

    The lists provided are:**MAX_ACTIVATING_TOKENS:**howwhatHimwhatFoundationhowthighsthatitEqu**TOKENS_AFTER_MAX_ACTIVATING_TOKEN:**muchtreatmentf')forstart?inox**TOP_POSITIVE_LOGITS:**erIietiquี્ષeriey**TOP_ACTIVATING_TEXTS:** 3. If I have enough money to buy a loaf of bread, will I have any change? If so, how much change? Okay, let's break down your money situation! **1. How user Did you go to the doctor? If yes, what treatment did he / she prescribe? model As a large language model, I don't have a https://docs.google.com/document/d/1o5ECrVC0cvxkMi8Himf8W2VWYeaL4yCfRBp_HL_nDIc/edit?usp= user Has any one created a forcefield like in sci-fi , if so what's it made of plasma? model Okay, let's break down the fascinating topic of force're affiliated with a university, check their internal grant programs. Many foundations (e.g., Schmidt Futures, Sloan Foundation) have small grants for early-stage AI research. *Focus on the novelty of your self-analysis/performance* "Do you think the impact of money on happiness differs for different people or in different circumstances? If so, how flat. Lift your hips off the floor, squeezing your glutes at the top.`how much` or `what treatment`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_12_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    사의
    1.05
    ס
    1.03
    కి
    0.99
     Yhat
    0.96
    РО
    0.95
     prostatic
    0.95
     Obstetrics
    0.94
     concordance
    0.92
     inaccur
    0.91
     therapeut
    0.91
    POSITIVE LOGITS
    er
    1.16
    I
    1.13
    i
    1.09
    et
    1.06
    iq
    1.06
    u
    1.03
    ี
    1.01
    ્ષ
    0.98
    erie
    0.96
    y
    0.95
    Activations Density 0.001%

    No Known Activations