© 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. 34-GEMMASCOPE-RES-131K
    7. 79448
    Prev
    Next
    INDEX
    Explanations

    news articles and hyperlinks

    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_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     androidx
    -1.30
     covid
    -0.97
     ۱۴۰۰
    -0.96
    androidx
    -0.93
     bg
    -0.93
    DMETHOD
    -0.89
     beni
    -0.86
    ädig
    -0.86
     Covid
    -0.84
    covid
    -0.84
    POSITIVE LOGITS
     officials
    1.07
    Permalink
    0.94
    官员
    0.93
    Associated
    0.90
     LOGIN
    0.86
    Mär
    0.86
     lavori
    0.84
    Related
    0.84
     Permalink
    0.83
     police
    0.81
    Activations Density 0.032%

    No Known Activations