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. 7739
    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
    INDOW
    1.11
     पड़ने
    1.11
    cheduler
    1.10
    Colleg
    1.06
    obst
    1.06
    簧
    1.05
     excuse
    1.02
     বঙ্গবন্ধ
    1.02
     ऑर्गेनाइजेशन
    1.02
     Salle
    1.01
    POSITIVE LOGITS
    ‭
    1.11
    ィ
    1.08
     Их
    1.08
    nungen
    1.06
    
    1.06
    tut
    1.06
    тия
    1.03
     disagreeable
    1.03
     tutt
    1.02
     godly
    1.01
    Activations Density 0.000%

    No Known Activations