Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 16-GEMMASCOPE-2-RES-262K
    4. 17680
    Prev
    Next
    INDEX
    Explanations

    figure skating

    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
    il
    0.77
    ul
    0.76
    us
    0.75
    ance
    0.75
    :
    0.75
    ar
    0.73
    ol
    0.73
    er
    0.70
    box
    0.70
    ir
    0.69
    POSITIVE LOGITS
    सलमान
    0.64
    メ
    0.64
    Лю
    0.63
     தெரிவித்துள்ளது
    0.62
     filePath
    0.60
    盟
    0.60
    HttpStatus
    0.59
    Salman
    0.59
    安倍
    0.59
    ܡ
    0.59
    Activations Density 0.006%

    No Known Activations