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. 7744
    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
     supplémentaire
    2.16
    લ
    2.02
    ฿
    2.00
     pois
    1.99
     રહ્યા
    1.97
    ंत्रिक
    1.97
     toga
    1.96
    Исход
    1.95
     Başkanı
    1.92
    ન
    1.91
    POSITIVE LOGITS
     ढंग
    2.58
    样的
    2.57
    ن
    2.50
    hift
    2.30
    al
    2.21
    ्य
    2.20
    おり
    2.14
    ︎
    2.13
    くちゃ
    2.13
    ۥ
    2.09
    Activations Density 0.087%

    No Known Activations