© 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. 44509
    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
    ;
    -1.08
     imprensa
    -0.99
    |
    -0.98
    而且
    -0.92
    ">
    -0.92
     in
    -0.91
     their
    -0.90
    –
    -0.88
     '*':
    -0.88
    ња
    -0.86
    POSITIVE LOGITS
    ローチ
    1.16
    Опис
    1.11
    
    1.02
    ȃ
    1.00
    "}")
    0.97
     encroachment
    0.96
    𐌿
    0.95
    amqp
    0.94
     كتب
    0.94
     mentes
    0.93
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.