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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 9-GEMMASCOPE-2-RES-262K
    4. 7711
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    gg-gs/gemma-scope-2-4b-it/resid_post
    Prompts (Dashboard)
    273,612 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    য়ে
    2.62
    ‍♀️
    2.62
     amide
    2.62
    !--
    2.60
    =\{\
    2.59
    beginner
    2.57
     crore
    2.54
    ={\
    2.52
    ый
    2.51
    ീയ
    2.40
    POSITIVE LOGITS
    𝐚
    2.76
    ف
    2.68
    ح
    2.65
    ो
    2.62
    ー
    2.57
    𝐩
    2.55
    el
    2.54
    ব
    2.51
    า
    2.50
    тті
    2.45
    Activations Density 0.073%

    No Known Activations