© 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. 22-GEMMASCOPE-RES-131K
    7. 127778
    Prev
    Next
    INDEX
    Explanations

    prefixes and list items

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    菒
    -1.77
     pérd
    -1.77
     eſſ
    -1.75
     intensif
    -1.73
     Septembre
    -1.66
    雠
    -1.66
     ſol
    -1.66
     TÉ
    -1.64
     RÉ
    -1.63
    鰯
    -1.62
    POSITIVE LOGITS
     and
    2.09
     or
    1.91
     but
    1.83
     during
    1.75
     with
    1.66
     takes
    1.52
     after
    1.49
     for
    1.45
     as
    1.41
     will
    1.35
    Activations Density 0.000%

    No Known Activations