© 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. 30945
    Prev
    Next
    INDEX
    Explanations

    billiard and dart games

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

    ppo, advantage, return, policy gradient

    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
    ANIM
    0.52
    諜
    0.50
    INDUST
    0.45
    ﾘ
    0.43
    び
    0.43
     लहर
    0.42
     LOOP
    0.42
    Loire
    0.42
    網
    0.42
    élène
    0.41
    POSITIVE LOGITS
     billi
    0.66
     tournaments
    0.64
     winnings
    0.64
     billiard
    0.64
     tournament
    0.61
     Tournament
    0.55
     bowling
    0.55
    🎱
    0.55
     players
    0.54
    Tournament
    0.53
    Activations Density 0.017%

    No Known Activations