© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 118053
    Prev
    Next
    INDEX
    Explanations

    any color

    np_acts-logits-general · gemini-2.5-flash-lite

    disguised items or concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     in
    0.53
     team
    0.50
     repre
    0.48
     on
    0.46
     #
    0.44
     don
    0.44
     pledge
    0.44
    paint
    0.43
     paul
    0.42
     Sharpe
    0.42
    POSITIVE LOGITS
    ב
    0.56
    ין
    0.51
    얌
    0.50
    انگ
    0.50
    ล์
    0.49
    어가
    0.49
    빗
    0.48
    іо
    0.47
     লুকিয়ে
    0.46
    둥
    0.46
    Activations Density 0.002%

    No Known Activations