© 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. 47090
    Prev
    Next
    INDEX
    Explanations

    contest, competition, spelling bee

    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
    easing
    -0.82
    bantu
    -0.78
    pagnes
    -0.74
    }$}
    -0.73
     Court
    -0.72
    temuan
    -0.72
     Booking
    -0.70
    Outlook
    -0.69
    ZD
    -0.69
    lė
    -0.69
    POSITIVE LOGITS
     Olymp
    1.39
     olymp
    1.14
     contestants
    1.07
     IMO
    1.04
     spelling
    1.02
     competition
    1.02
    лимпи
    1.00
     competitors
    0.98
     Mathematical
    0.95
     team
    0.93
    Activations Density 0.048%

    No Known Activations