© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 12164
    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
     you
    -1.13
     pulito
    -1.03
     it
    -0.98
     cost
    -0.97
     extra
    -0.94
    AND
    -0.93
    geſ
    -0.91
    </b>
    -0.91
     The
    -0.90
     myriad
    -0.90
    POSITIVE LOGITS
    Orchid
    1.07
     coordonnées
    1.07
    SONY
    1.05
    🛋
    0.97
    贖
    0.96
    Kemudian
    0.94
     awar
    0.94
    bilis
    0.92
     [?]
    0.91
    AddField
    0.88
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.