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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-12B-IT
    3. 12-GEMMASCOPE-2-RES-16K
    4. 7356
    Prev
    Next
    INDEX
    Explanations

    little ones

    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
     Та
    1.27
     Э
    1.19
     الشعر
    1.15
     ifs
    1.15
     busses
    1.05
     manures
    1.05
     elution
    1.05
    ্যালি
    1.04
     которая
    1.03
     grasses
    1.03
    POSITIVE LOGITS
    z
    1.40
    inthe
    1.08
    GI
    1.01
    ess
    0.98
    <0x8B>
    0.97
    au
    0.96
    uu
    0.93
    Prevention
    0.93
    uw
    0.93
    Foundation
    0.92
    Activations Density 0.306%

    No Known Activations