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. 7642
    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
    นิยม
    1.23
    ύ
    1.19
    sterdam
    1.15
    icelli
    1.13
    텍
    1.13
     euismod
    1.13
    тів
    1.11
    ্যাল
    1.08
     koristiti
    1.06
    ের
    1.06
    POSITIVE LOGITS
    सभी
    1.47
     esteemed
    1.45
     Darryl
    1.38
    ו
    1.35
     touted
    1.34
    ança
    1.33
     whereabouts
    1.33
    ganos
    1.32
     welds
    1.31
     adanya
    1.29
    Activations Density 0.000%

    No Known Activations