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. 7736
    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
    с
    3.03
    Bump
    2.74
     catalyze
    2.64
    ine
    2.61
    не
    2.50
    etary
    2.47
    ⁡</
    2.44
    ಾ
    2.42
    acharya
    2.39
    나
    2.38
    POSITIVE LOGITS
    석
    2.46
    িকাংশ
    2.31
    handsome
    2.28
    जानकारी
    2.25
     Dla
    2.24
     continuación
    2.23
    ु
    2.22
    itäts
    2.22
     interesados
    2.17
    ו
    2.15
    Activations Density 0.019%

    No Known Activations