© 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. 30248
    Prev
    Next
    INDEX
    Explanations

    wrestling and grappling

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ânica
    -0.77
    zczy
    -0.75
    vení
    -0.72
     Bernadette
    -0.72
     Spells
    -0.72
    Missions
    -0.72
     آتش
    -0.71
     acorns
    -0.71
    فق
    -0.70
    enciais
    -0.69
    POSITIVE LOGITS
     wrestling
    3.41
     wrestle
    3.02
     Wrestling
    2.73
     wrestled
    2.55
    Wrestling
    2.45
     wrestlers
    2.44
     wrestler
    2.34
     wrest
    2.14
     Wrestle
    2.06
     grappling
    2.05
    Activations Density 0.023%

    No Known Activations