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. 7698
    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
    ी
    1.14
     uneas
    1.06
     Nand
    0.98
     crowd
    0.97
     maggior
    0.94
     crowds
    0.93
     puzzling
    0.91
     displeasure
    0.91
     quitting
    0.91
     pos
    0.91
    POSITIVE LOGITS
    
    1.34
     $\}$
    1.05
    
    1.03
    \%)
    0.99
    ганда
    0.96
    मत
    0.94
    \%
    0.92
    
    0.90
     perpetrated
    0.90
    inject
    0.89
    Activations Density 1.421%

    No Known Activations