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. 7623
    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
     searing
    1.53
    ahankan
    1.49
    𝗬
    1.41
     recession
    1.34
     decidedly
    1.33
    deceased
    1.33
     stalwart
    1.32
    y
    1.31
     מו
    1.31
    paintbrush
    1.31
    POSITIVE LOGITS
    ibilit
    1.38
    การ
    1.26
     গিয়ে
    1.22
     compart
    1.19
    ongi
    1.19
     pictureBox
    1.18
    コーデ
    1.17
    يجي
    1.16
     piensan
    1.16
    atura
    1.15
    Activations Density 0.000%

    No Known Activations