© 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. 15596
    Prev
    Next
    INDEX
    Explanations

    copy writer, constructor, shop, paste, ratio, copyright

    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
    '
    -2.77
     are
    -2.45
    (
    -1.97
     you
    -1.88
    ’
    -1.85
    \
    -1.83
    .
    -1.82
     in
    -1.81
    </h2>
    -1.71
     have
    -1.70
    POSITIVE LOGITS
    𐐪
    2.41
    èdent
    2.36
     giapponese
    2.08
    羕
    2.08
    "}}>
    1.80
     पनि
    1.80
    wanzig
    1.78
    磻
    1.76
    噚
    1.75
     erwähnt
    1.73
    Activations Density 0.020%

    No Known Activations