© 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-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 7981
    Prev
    Next
    INDEX
    Explanations

    wrestling and poor performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ⛹
    0.51
     Fermat
    0.42
    marginal
    0.41
    equivalence
    0.41
     تسه
    0.41
    cones
    0.41
     playerData
    0.40
     игровой
    0.39
    lastIndexOf
    0.39
    🎷
    0.39
    POSITIVE LOGITS
     wrestling
    1.69
     wrestlers
    1.65
     wrestler
    1.55
     wrestled
    1.49
     WWE
    1.48
     Wrestling
    1.46
    WWE
    1.42
     Wrestle
    1.41
     wrestle
    1.37
     Wrest
    1.29
    Activations Density 0.055%

    No Known Activations