© 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. 98911
    Prev
    Next
    INDEX
    Explanations

    template, module, type, class, dialog

    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
    licopter
    -2.16
    >`;
    -1.94
     apropri
    -1.91
    iress
    -1.89
    alers
    -1.88
     connaissent
    -1.85
     handels
    -1.84
    ☫
    -1.80
    )++;
    -1.77
     saia
    -1.76
    POSITIVE LOGITS
     at
    2.08
    '
    2.02
    \
    1.91
     with
    1.83
     on
    1.82
     e
    1.73
     or
    1.69
     enkele
    1.66
     is
    1.63
     m
    1.54
    Activations Density 0.024%

    No Known Activations