© 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. 58225
    Prev
    Next
    INDEX
    Explanations

    closing xml/html tags

    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
    
    -1.81
    钇
    -1.79
    ’
    -1.66
    $*$
    -1.63
     hermosas
    -1.62
     inauguración
    -1.58
     severa
    -1.56
    ᨈ
    -1.56
    ilty
    -1.55
    previously
    -1.55
    POSITIVE LOGITS
     with
    1.96
     based
    1.85
     that
    1.75
     from
    1.75
     to
    1.70
     for
    1.68
     most
    1.66
     more
    1.62
     mostly
    1.57
    ưới
    1.55
    Activations Density 0.001%

    No Known Activations