© 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. 7392
    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
    antik
    -0.95
    萸
    -0.95
    疣
    -0.94
     همه
    -0.93
    ようだ
    -0.91
    4
    -0.90
    lização
    -0.89
     you
    -0.89
    isateurs
    -0.88
    Warna
    -0.88
    POSITIVE LOGITS
     Notwendigkeit
    0.97
     Ciências
    0.94
     olhando
    0.93
    管道
    0.91
     asequ
    0.90
     anecd
    0.89
     Energía
    0.88
     confiable
    0.87
    Pure
    0.87
     acrescent
    0.87
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.