© 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-262K
    7. 28479
    Prev
    Next
    INDEX
    Explanations

    ¡Claro o ¿qué

    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_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
    ),
    0.40
    ).
    0.39
    )
    0.38
    );
    0.38
    ,
    0.38
     نیز
    0.37
    ،
    0.37
    )،
    0.36
    -
    0.34
    :
    0.34
    POSITIVE LOGITS
    כל
    0.35
    什麼
    0.33
     ऐसा
    0.32
     những
    0.32
     upto
    0.31
     इस
    0.31
    যে
    0.31
     результат
    0.31
     faptul
    0.30
    по
    0.29
    Activations Density 0.088%

    No Known Activations