© 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. 83849
    Prev
    Next
    INDEX
    Explanations

    describing what is normal

    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
    </strong>
    -2.16
     while
    -1.54
    řízen
    -1.48
    </em>
    -1.46
    }{
    -1.41
    etsk
    -1.38
     sartén
    -1.37
     from
    -1.36
    Huile
    -1.36
     soothe
    -1.34
    POSITIVE LOGITS
    os
    1.95
    oo
    1.79
    </h5>
    1.78
     tranquillo
    1.65
    It
    1.63
    However
    1.61
    ts
    1.60
    芣
    1.60
    as
    1.57
    m
    1.57
    Activations Density 0.037%

    No Known Activations