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. 7655
    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
    ा
    1.45
    InitFlag
    1.30
    ک
    1.15
     alight
    1.15
     dotycz
    1.10
    ت
    1.07
    carrot
    1.06
    aol
    1.05
     graphically
    1.04
     lacking
    1.03
    POSITIVE LOGITS
    го
    1.43
    🏻
    1.21
    ছে
    1.17
    𝗲
    1.16
    arbe
    1.15
     άλλ
    1.12
    𝐢
    1.10
    tedir
    1.10
    ει
    1.08
     been
    1.07
    Activations Density 0.045%

    No Known Activations