© 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. 4880
    Prev
    Next
    INDEX
    Explanations

    indicates whether True

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

    static boolean field

    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
    最高の
    0.42
    峯
    0.40
    ที่เรา
    0.39
    蚯
    0.39
    ქვენ
    0.39
    驥
    0.38
    適切な
    0.38
    魟
    0.38
     প্রয়োজনীয়
    0.38
     તમારા
    0.38
    POSITIVE LOGITS
     bool
    2.14
    bool
    2.05
     boolean
    1.98
    boolean
    1.85
     Boolean
    1.77
    Boolean
    1.70
     Bool
    1.70
     BOOLE
    1.65
    Bool
    1.64
     whether
    1.61
    Activations Density 0.029%

    No Known Activations