© 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. 6997
    Prev
    Next
    INDEX
    Explanations

    Always followed by action

    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
    ⃨
    -2.08
    劼
    -1.91
    汌
    -1.90
    ⻓
    -1.88
    geſ
    -1.88
     недорого
    -1.88
    
    -1.86
    」，
    -1.84
     that
    -1.79
    ierend
    -1.72
    POSITIVE LOGITS
     =
    2.23
    Always
    1.98
    as
    1.95
    In
    1.78
    It
    1.76
    媖
    1.73
    Many
    1.70
    they
    1.68
    ࿚
    1.66
    灕
    1.62
    Activations Density 0.004%

    No Known Activations