© 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
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17553
    Prev
    Next
    INDEX
    Explanations

    chess

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

    chess

    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_53_width_65k_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
     témo
    0.42
     pompe
    0.41
    埚
    0.40
    戽
    0.40
     गाय
    0.39
     PMA
    0.39
    フト
    0.39
     SCRE
    0.38
    ળ
    0.38
    菈
    0.38
    POSITIVE LOGITS
     chess
    2.77
    Chess
    2.58
     Chess
    2.58
    chess
    2.39
     chessboard
    2.20
    棋
    2.17
     शतरंज
    2.08
    chessboard
    1.82
    象棋
    1.79
    ♟
    1.66
    Activations Density 0.040%

    No Known Activations