© 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. 20510
    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
    there
    -1.93
     before
    -1.73
    身为
    -1.70
     it
    -1.68
    ㈦
    -1.63
     regarding
    -1.61
     setor
    -1.60
     なく
    -1.57
     only
    -1.55
     an
    -1.53
    POSITIVE LOGITS
     печени
    1.70
     fiasco
    1.67
     fidé
    1.63
     agresión
    1.55
     mayoría
    1.54
     aparência
    1.53
     impromptu
    1.52
    HttpFoundation
    1.51
     兔子
    1.50
     decorados
    1.49
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.