© 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. 31-GEMMASCOPE-2-RES-65K
    7. 56537
    Prev
    Next
    INDEX
    Explanations

    foreign name in parentheses

    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_31_width_65k_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
     aeronaut
    0.41
    MiddleLeft
    0.41
     geopol
    0.40
     housework
    0.40
     photovolta
    0.39
    💆
    0.38
    ⑵
    0.38
    Functional
    0.38
    ظيف
    0.38
    ージェ
    0.38
    POSITIVE LOGITS
     louder
    0.41
     कितना
    0.39
     );
    0.38
    )$;
    0.36
    always
    0.35
     อังกฤษ
    0.35
     którą
    0.35
     ក
    0.34
    उस
    0.34
     pronounce
    0.34
    Activations Density 0.037%

    No Known Activations