© 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. 466
    Prev
    Next
    INDEX
    Explanations

    grouping symbols: parentheses, brackets, quotes

    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
    f
    0.66
     at
    0.66
     to
    0.65
     τη
    0.64
     u
    0.64
    S
    0.62
    in
    0.61
     tại
    0.61
    0
    0.61
     nõ
    0.59
    POSITIVE LOGITS
    ی
    0.90
    ни
    0.79
    т
    0.78
     brackets
    0.74
    括号
    0.69
    ન
    0.69
     parenthesis
    0.68
    و
    0.68
    ور
    0.66
    udades
    0.65
    Activations Density 0.239%

    No Known Activations