© 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. 47806
    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
    」，
    -1.09
     wherein
    -0.94
     Muitos
    -0.94
     verminder
    -0.93
    塒
    -0.92
     būs
    -0.91
     posiad
    -0.90
     regionale
    -0.90
     Talvez
    -0.90
     pasangan
    -0.90
    POSITIVE LOGITS
    ramos
    0.98
     engaging
    0.98
     ''
    0.97
    <sup>
    0.95
    部长
    0.94
    方的
    0.92
     impressively
    0.90
    tamente
    0.89
     amusing
    0.89
    悻
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.