© 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-3-12B-IT
    5. 24-GEMMASCOPE-2-RES-262K
    7. 1902
    Prev
    Next
    INDEX
    Explanations

    languages asking about specifics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-it/resid_post/layer_24_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
    或其他
    0.34
    jac
    0.31
    または
    0.29
    Denote
    0.29
    '.
    0.29
     предназначен
    0.29
    /
    0.29
    Returning
    0.28
    Entering
    0.28
    Mother
    0.28
    POSITIVE LOGITS
     çok
    0.50
     bugün
    0.49
     ciddi
    0.44
     jsme
    0.44
     많
    0.43
     많은
    0.43
    ပြီ
    0.43
     şimdi
    0.43
     بھی
    0.42
    ujourd
    0.42
    Activations Density 0.002%

    No Known Activations