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. 7704
    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
    traj
    1.12
    ൈ
    1.09
     infect
    1.07
     والف
    1.05
     다
    1.05
    ainment
    1.04
     나와
    1.04
    绎
    1.02
     ты
    1.02
    tutorials
    1.00
    POSITIVE LOGITS
     సందర్భంగా
    1.30
     kapsamında
    1.28
     adegu
    1.20
     ustawy
    1.20
     mendatang
    1.19
    Сере
    1.12
    ENERGY
    1.11
     digelar
    1.11
     aimed
    1.10
     zusätz
    1.07
    Activations Density 0.086%

    No Known Activations