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. 7702
    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
    ن
    2.53
    en
    2.27
    ল
    1.94
    ження
    1.91
     kert
    1.88
     agar
    1.83
    न
    1.81
    ations
    1.80
     ponds
    1.79
    Saat
    1.75
    POSITIVE LOGITS
     admirably
    1.73
    াজ
    1.66
     przyczyn
    1.65
    lysis
    1.55
    ἥ
    1.50
     direta
    1.48
    লা
    1.47
     cinética
    1.47
     суще
    1.45
     microbe
    1.45
    Activations Density 0.000%

    No Known Activations