© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 63624
    Prev
    Next
    INDEX
    Explanations

    ball sports and games

    np_acts-logits-general · gemini-2.5-flash-lite

    ball

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Evaluating
    0.46
    シート
    0.45
    श्रे
    0.45
    降り
    0.43
    готовить
    0.43
    evaluated
    0.43
    猙
    0.42
    መን
    0.42
    ზ
    0.42
    荆
    0.41
    POSITIVE LOGITS
     ball
    1.23
     Ball
    1.03
    球
    1.00
     球
    0.99
     balls
    0.94
     bola
    0.93
    Ball
    0.91
     الكرة
    0.91
     BALL
    0.90
     Balls
    0.88
    Activations Density 0.046%

    No Known Activations