© 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. 47891
    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
    {"{
    -1.07
    били
    -0.96
    verbatim
    -0.95
     diseñar
    -0.93
    ><?
    -0.92
    🩻
    -0.92
    "]="
    -0.91
    eded
    -0.90
     taką
    -0.90
    帮我
    -0.89
    POSITIVE LOGITS
     vitally
    0.98
    本日
    0.85
     徒歩
    0.84
    Berat
    0.83
     millioner
    0.81
    ilus
    0.81
    السلام
    0.81
     posta
    0.81
    Waga
    0.81
     einige
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.