© 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. 9721
    Prev
    Next
    INDEX
    Explanations

    poker tournaments and tables

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

    poker, chess, and bluffing games

    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_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
     functionalities
    0.44
    図柄
    0.42
     Synth
    0.42
    辊
    0.40
     laz
    0.39
     swirling
    0.39
     lightbox
    0.39
     splendour
    0.39
    🥚
    0.39
     Cursor
    0.38
    POSITIVE LOGITS
     poker
    1.22
    Poker
    1.17
     Poker
    1.16
     покер
    1.05
     پوکر
    0.78
     tournaments
    0.69
     tournament
    0.68
     grinders
    0.61
    扑
    0.60
     Tournament
    0.60
    Activations Density 0.142%

    No Known Activations