© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113053
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    儡
    -0.97
     Verfasser
    -0.97
     vaste
    -0.95
    怎么能
    -0.92
    andı
    -0.91
     precisa
    -0.91
     tapis
    -0.90
     Andalucía
    -0.90
    囪
    -0.89
     Málaga
    -0.88
    POSITIVE LOGITS
     these
    1.16
    ’
    1.03
    ㎏
    0.94
    値下げ
    0.93
    docker
    0.91
    rantz
    0.85
    عالی
    0.84
    ด้าน
    0.84
     with
    0.83
    -
    0.82
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.