© 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. 31-GEMMASCOPE-2-RES-65K
    7. 52829
    Prev
    Next
    INDEX
    Explanations

    bowling and projectiles

    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_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     treadmill
    0.43
     நடை
    0.42
    NewDecoder
    0.41
    副作用
    0.41
     Watches
    0.40
     hedon
    0.40
    腫
    0.40
     dancer
    0.39
     институт
    0.39
     biochemical
    0.38
    POSITIVE LOGITS
     projectiles
    0.71
     bowling
    0.70
     projectile
    0.65
    🎳
    0.61
     ক্রিকেট
    0.61
    Projectile
    0.59
     throwing
    0.58
     Softball
    0.58
    球
    0.57
    🥎
    0.57
    Activations Density 0.070%

    No Known Activations