© 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. 45413
    Prev
    Next
    INDEX
    Explanations

    using something

    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
     It
    -2.02
    EdgeInsets
    -1.77
    </em>
    -1.75
     if
    -1.73
    因为它
    -1.60
    ไป
    -1.59
     
    -1.59
     is
    -1.59
    ebly
    -1.59
    -1.57
    POSITIVE LOGITS
     of
    2.59
     but
    1.88
     this
    1.71
    際には
    1.65
    تصویر
    1.62
    龌
    1.52
     및
    1.47
     namun
    1.46
    つづく
    1.45
    呸
    1.45
    Activations Density 0.161%
    No Known Activations