© 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. 64329
    Prev
    Next
    INDEX
    Explanations

    HTML tags and attributes

    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
    0
    -1.21
     to
    -1.08
     will
    -1.04
    ("");
    -1.02
     all
    -1.01
    irmanship
    -1.01
     экономических
    -0.96
     only
    -0.95
     Economic
    -0.95
     two
    -0.93
    POSITIVE LOGITS
     TAMBÉM
    1.08
    ೦
    1.05
    覿
    1.02
    可以让
    1.00
     nạ
    1.00
    aville
    0.99
    摀
    0.98
     récup
    0.98
    躥
    0.98
     muni
    0.97
    Activations Density 0.003%

    No Known Activations