© 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. 71638
    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
     or
    -1.97
     and
    -1.91
     for
    -1.88
     in
    -1.71
     to
    -1.69
     such
    -1.58
     with
    -1.56
     at
    -1.53
     which
    -1.44
     where
    -1.39
    POSITIVE LOGITS
    romolecules
    1.57
     yyb
    1.52
     suro
    1.52
    Enregistrer
    1.52
    ONYMOUS
    1.48
     tenemos
    1.47
     corrom
    1.45
    鸶
    1.45
     we
    1.43
     мы
    1.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.