© 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. 127944
    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
    ͈
    -1.10
     or
    -1.00
     типа
    -0.95
    雷霆
    -0.91
     ziehen
    -0.90
    TZ
    -0.90
     addressee
    -0.88
    天堂
    -0.88
     be
    -0.88
    蛋
    -0.88
    POSITIVE LOGITS
    身后
    1.09
     litri
    1.04
     flamengo
    1.02
     Kompetenz
    0.99
    ⅕
    0.96
     Bearbeitung
    0.96
     heuti
    0.94
    ⅛
    0.94
     Catalana
    0.92
     bicchiere
    0.92
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.