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. 7629
    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
    us
    1.65
    AM
    1.58
    اور
    1.47
    B
    1.42
    াতি
    1.41
    ان
    1.40
    a
    1.40
    IM
    1.40
     прошу
    1.37
    মেয়
    1.36
    POSITIVE LOGITS
     whirl
    1.66
     unjust
    1.60
     Arbor
    1.56
     anise
    1.53
     hexagon
    1.51
     goblin
    1.50
     misty
    1.48
     thirties
    1.48
     апреле
    1.46
     Glitter
    1.46
    Activations Density 0.008%

    No Known Activations