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. 7746
    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
     kau
    0.95
    ள்ளதாக
    0.95
    <unused575>
    0.94
     Eureka
    0.94
    馇
    0.92
     picnic
    0.90
     తయారు
    0.89
    된
    0.89
     adlı
    0.87
     justement
    0.87
    POSITIVE LOGITS
     midfielder
    1.04
     midfielders
    0.95
     winger
    0.93
    Messi
    0.91
    OrderStatus
    0.91
     LastName
    0.91
    Tottenham
    0.89
     nonchal
    0.89
     بیٹنگ
    0.88
     Tuchel
    0.87
    Activations Density 0.027%

    No Known Activations