© 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. 32660
    Prev
    Next
    INDEX
    Explanations

    statistical and mathematical functions

    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
     Parece
    -1.05
    illust
    -0.99
    }$​
    -0.96
     ١
    -0.95
     outil
    -0.95
     ٢
    -0.94
     chré
    -0.93
     /*#__
    -0.93
     افرادی
    -0.93
     koja
    -0.92
    POSITIVE LOGITS
     they
    1.20
     by
    1.12
     using
    0.94
     our
    0.93
    حسب
    0.92
     ihnen
    0.91
    They
    0.90
     они
    0.90
     プラン
    0.89
     your
    0.88
    Activations Density 0.013%

    No Known Activations