© 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
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6800
    Prev
    Next
    INDEX
    Explanations

    bodily reactions and requests

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Formen
    1.06
    Logo
    1.05
     Madsen
    1.05
    Terms
    1.04
    スペック
    1.04
    盹
    1.04
    dü
    1.03
     Wam
    1.02
    烜
    1.02
     Setup
    1.01
    POSITIVE LOGITS
     murderers
    1.29
     granddaughters
    1.27
    子女
    1.26
    extension
    1.23
    רות
    1.22
     suburb
    1.19
    roses
    1.18
    iany
    1.17
    线的
    1.14
    uric
    1.13
    Activations Density 0.032%

    No Known Activations