© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 47261
    Prev
    Next
    INDEX
    Explanations

    Background of the Art

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    phis
    -0.73
    nok
    -0.72
     fiscales
    -0.69
    ={{
    -0.69
     Gallimard
    -0.67
    Références
    -0.67
    握
    -0.66
    stringify
    -0.65
    lok
    -0.65
    %}
    -0.65
    POSITIVE LOGITS
    DESK
    0.74
     cabinets
    0.72
     bảo
    0.71
     analyses
    0.70
    beda
    0.70
    茸
    0.70
     Pola
    0.69
     Dewan
    0.69
     ろう
    0.69
    後は
    0.68
    Activations Density 0.015%

    No Known Activations