© 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. 64449
    Prev
    Next
    INDEX
    Explanations

    men and women

    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
     Руси
    -1.06
     工事
    -1.05
    ＝
    -1.04
    assertThrows
    -1.03
     المنتج
    -1.02
    سية
    -1.02
    Supplemental
    -0.98
    śred
    -0.97
     ujarnya
    -0.97
     disait
    -0.96
    POSITIVE LOGITS
    excell
    1.02
     diversas
    1.00
     mentre
    0.98
     eastern
    0.96
     diversos
    0.96
    tská
    0.90
    為に
    0.90
     meager
    0.90
     wymaga
    0.89
     This
    0.88
    Activations Density 0.132%

    No Known Activations