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. 7687
    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
    ع
    4.54
    ف
    4.28
    فري
    3.23
    an
    3.03
    า
    3.01
    לע
    2.83
    علم
    2.82
    y
    2.81
    ので
    2.76
    z
    2.71
    POSITIVE LOGITS
    ńca
    3.03
     Él
    2.84
    全年
    2.71
     dessen
    2.67
    ل
    2.54
    cmds
    2.48
     Infiniti
    2.48
    С
    2.46
    
    2.44
    ારા
    2.43
    Activations Density 0.048%

    No Known Activations