© 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. 14166
    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
    ingan
    -0.97
    ratory
    -0.95
     tudom
    -0.94
    сайт
    -0.93
     Wikispecies
    -0.91
    ㄴ
    -0.89
     Performed
    -0.89
    ofing
    -0.89
    廚房
    -0.89
    drawImage
    -0.88
    POSITIVE LOGITS
     aimed
    1.02
    yfik
    0.90
     gemeint
    0.88
     functioned
    0.88
    طاء
    0.88
    ビニ
    0.88
     निम्
    0.88
    ToPoint
    0.86
    ئية
    0.86
     between
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.