© 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. 90432
    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
    atá
    -0.91
    信頼
    -0.88
     CAA
    -0.87
    謳
    -0.86
    꼼
    -0.85
    strnc
    -0.85
    女性の
    -0.84
     even
    -0.84
    astră
    -0.84
    Oof
    -0.83
    POSITIVE LOGITS
    廰
    1.12
    algebras
    1.02
     rosse
    0.93
     harde
    0.92
     latine
    0.91
     autonome
    0.90
     中心
    0.88
    XLSX
    0.88
     contraire
    0.88
     premiers
    0.86
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.