© 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. 58198
    Prev
    Next
    INDEX
    Explanations

    fulfillment center

    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
    泐
    -1.99
     are
    -1.96
     видит
    -1.94
    猻
    -1.84
    5
    -1.84
    êmio
    -1.73
    ”;
    -1.73
     включает
    -1.70
    ucchini
    -1.66
    iocene
    -1.65
    POSITIVE LOGITS
     
    1.77
     is
    1.74
    </h2>
    1.71
     désolés
    1.66
    了我
    1.63
     fala
    1.62
     می‌
    1.58
     mochila
    1.57
    тех
    1.55
     Chile
    1.53
    Activations Density 0.005%

    No Known Activations