© 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. 68681
    Prev
    Next
    INDEX
    Explanations

    defining concepts

    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
    Negative Logits
     時代
    -1.93
    已經
    -1.82
    และ
    -1.79
     esclusivamente
    -1.73
    。”
    -1.68
    This
    -1.66
    </h2>
    -1.61
     provenant
    -1.61
    After
    -1.60
     및
    -1.60
    POSITIVE LOGITS
     for
    2.11
     it
    1.80
     they
    1.71
     like
    1.71
     a
    1.69
     not
    1.67
     to
    1.61
     in
    1.55
    malige
    1.52
     by
    1.47
    Activations Density 0.050%

    No Known Activations