© 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. 123813
    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
    ↵
    -0.94
     привле
    -0.91
    श्चित
    -0.91
    hướng
    -0.91
    notas
    -0.90
    セミナー
    -0.87
    大战
    -0.87
     gdy
    -0.84
    máy
    -0.84
     สวย
    -0.83
    POSITIVE LOGITS
    arela
    1.05
     Including
    1.02
     допо
    0.98
    стреча
    0.94
     mãi
    0.94
     There
    0.93
    paña
    0.92
     cantora
    0.91
    According
    0.90
     具
    0.90
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.