© 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. 36342
    Prev
    Next
    INDEX
    Explanations

    game decisions and player actions

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

    player move or decision

    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
    DATE
    0.50
    載
    0.49
    檔案
    0.47
     DATE
    0.46
     בד
    0.44
    Дата
    0.44
     धार
    0.43
    壹百
    0.43
    裒
    0.43
    fichier
    0.43
    POSITIVE LOGITS
     decision
    0.78
     player
    0.76
     decisions
    0.76
     actions
    0.66
     action
    0.62
     players
    0.62
     Decision
    0.62
     dönt
    0.61
     jogador
    0.60
    decision
    0.60
    Activations Density 0.035%

    No Known Activations