© 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. 2619
    Prev
    Next
    INDEX
    Explanations

    printing, article, restaurant

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

    natural language, programming, learning

    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
    Melitaea
    0.55
    鶚
    0.54
     張
    0.52
    思議
    0.51
    ColorBit
    0.51
     鳥
    0.51
    Benzyl
    0.50
    ныгы
    0.50
    গানি
    0.50
     劉
    0.50
    POSITIVE LOGITS
    的
    0.73
    对
    0.71
    与
    0.70
    在
    0.69
    按
    0.68
    和
    0.68
    向
    0.67
    可以
    0.66
    信息
    0.66
    能够
    0.66
    Activations Density 0.001%

    No Known Activations