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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-262K
    7. 20275
    Prev
    Next
    INDEX
    Explanations

    ball and bounce actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_262k_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
    出力
    0.82
    愕
    0.71
     complained
    0.69
    CES
    0.69
    ಶಿ
    0.67
     বসিয়া
    0.67
     bulldozer
    0.66
    രെ
    0.66
    ಕ್ಷ
    0.66
    稼
    0.65
    POSITIVE LOGITS
     bounces
    1.12
     bouncing
    1.06
    球
    0.99
     rebounded
    0.97
     bouncy
    0.96
     bounce
    0.96
     balls
    0.95
     bounced
    0.94
     thrown
    0.92
     ball
    0.92
    Activations Density 0.046%

    No Known Activations