© 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. 42487
    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
    Begriff
    -1.08
     Гон
    -1.01
    が残
    -1.00
    GRUPO
    -1.00
     leído
    -0.99
    必要がある
    -0.99
    鈊
    -0.99
    çok
    -0.97
     oído
    -0.96
     extérieure
    -0.96
    POSITIVE LOGITS
    SharedCtor
    1.05
    kies
    1.02
    doms
    0.97
    J
    0.93
    L
    0.93
    有
    0.92
     and
    0.90
    使
    0.90
    idane
    0.90
     Foreword
    0.89
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.