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. 7764
    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
     pong
    1.09
     diversi
    1.07
     cuarto
    1.05
    ெட்
    1.03
    매
    1.02
    わけで
    0.99
     Promised
    0.99
    ^{-}$
    0.98
    MORDOR
    0.98
     Bila
    0.98
    POSITIVE LOGITS
    tion
    1.40
    tired
    1.30
    ج
    1.27
    ся
    1.22
    な
    1.21
    yaxis
    1.20
     venu
    1.19
     subscrib
    1.19
     ráp
    1.16
     therefrom
    1.15
    Activations Density 0.118%

    No Known Activations