© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9774
    Prev
    Next
    INDEX
    Explanations

    bowling and billiard room

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

    bowling

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

    bowling

    np_max-act-logits · claude-4-5-sonnetTriggered by @skarne
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_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
     jihad
    0.42
    騫
    0.41
    Atl
    0.40
    地面
    0.40
     Eritrea
    0.40
     Saif
    0.39
     monod
    0.39
    সাহ
    0.38
     Atl
    0.38
     Antoni
    0.38
    POSITIVE LOGITS
     bowling
    1.02
     bowlers
    0.92
    🎳
    0.90
    Bowling
    0.86
     bowled
    0.79
     bowler
    0.79
     Bowling
    0.77
     गेंदबाज
    0.71
     billi
    0.71
     गेंदबाजी
    0.65
    Activations Density 0.162%

    No Known Activations