© 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. 16-GEMMASCOPE-2-RES-262K
    7. 3738
    Prev
    Next
    INDEX
    Explanations

    bulleted lists

    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_16_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
    ia
    0.73
     an
    0.66
    _$
    0.66
    Pot
    0.65
    ian
    0.63
     (
    0.62
    TI
    0.62
    SI
    0.61
    se
    0.61
    Equation
    0.61
    POSITIVE LOGITS
    ж
    0.75
    ра
    0.75
    ווי
    0.73
    о
    0.71
     причин
    0.67
    са
    0.63
    де
    0.63
    ной
    0.62
    方式
    0.62
    slidesPerGroup
    0.62
    Activations Density 0.029%

    No Known Activations