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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 9496
    Prev
    Next
    INDEX
    Explanations

    Warhammer tabletop RPGs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_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
     mux
    0.40
     persistently
    0.40
    コンサート
    0.40
     (^
    0.39
     involuntary
    0.39
    RETURNTRANSFER
    0.38
    uelles
    0.37
     emitted
    0.37
    丄
    0.37
     responds
    0.36
    POSITIVE LOGITS
     Warhammer
    1.19
     tabletop
    1.08
     miniatures
    1.02
     RPG
    0.89
     game
    0.86
    玩家
    0.82
    Dice
    0.81
     rpg
    0.80
     dice
    0.79
    Game
    0.79
    Activations Density 0.038%

    No Known Activations