© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42065
    Prev
    Next
    INDEX
    Explanations

    kicking

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

    kick, kicked, kicking

    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
    Not in Any Lists

    No Comments

    Negative Logits
    Collision
    0.50
    しい
    0.50
     đảo
    0.47
    Vocabulary
    0.47
    рования
    0.47
    ociaż
    0.47
    ^{-}$
    0.47
    케
    0.46
    スプレイ
    0.46
    ലൈ
    0.45
    POSITIVE LOGITS
     kicking
    1.02
     kicked
    0.93
     kicks
    0.92
     kick
    0.89
     Kick
    0.87
    踢
    0.82
    kick
    0.80
    Kick
    0.80
     kickoff
    0.78
    蹬
    0.75
    Activations Density 0.038%

    No Known Activations