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. 7664
    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
    menus
    1.16
    plexity
    1.15
    ərbay
    1.13
    ascape
    1.13
    翮
    1.12
     Genève
    1.11
     excepted
    1.10
    cribed
    1.10
    ினர்
    1.09
     apologized
    1.09
    POSITIVE LOGITS
    शुभ
    1.19
     expl
    1.16
     กระ
    1.14
     desto
    1.13
    äng
    1.12
     يب
    1.08
     메
    1.07
     gdje
    1.07
    마
    1.07
     ボ
    1.06
    Activations Density 0.000%

    No Known Activations