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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 29-GEMMASCOPE-2-RES-262K
    4. 52839
    Prev
    Next
    INDEX
    Explanations

    letters in a list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_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
    结束
    0.72
     quick
    0.69
     nhanh
    0.68
     quickly
    0.67
     subsection
    0.66
    訣
    0.64
     Ending
    0.63
     Subsection
    0.63
    Ending
    0.62
    Hus
    0.62
    POSITIVE LOGITS
    フェア
    0.67
     Syrian
    0.66
    ɕ
    0.65
     Fair
    0.65
    の一部
    0.65
    Fair
    0.64
     ולא
    0.64
    itoria
    0.62
    rela
    0.62
     aantal
    0.62
    Activations Density 0.007%

    No Known Activations