© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 15507
    Prev
    Next
    INDEX
    Explanations

    underscores as separators

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     ..."
    -1.98
    硖
    -1.97
     it
    -1.85
     The
    -1.80
    ...."
    -1.76
     wiederhol
    -1.73
    ığımız
    -1.72
     This
    -1.69
    
    -1.68
     There
    -1.67
    POSITIVE LOGITS
    ↵
    2.64
    ᠌
    1.89
     incredi
    1.83
    ペーン
    1.79
     résistance
    1.75
    柃
    1.73
    愎
    1.73
    ↵↵
    1.71
    鯢
    1.69
    क्टर
    1.68
    Activations Density 0.019%

    No Known Activations