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. 7686
    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
    时候
    1.51
    िका
    1.47
    இ
    1.44
     FileName
    1.43
    ن
    1.40
    Lint
    1.38
    chunk
    1.35
    ا
    1.30
    j
    1.30
    이크
    1.29
    POSITIVE LOGITS
    illaume
    1.53
     vực
    1.53
     inclination
    1.43
    iaus
    1.42
     immigration
    1.42
    pence
    1.41
     parole
    1.41
     Australie
    1.40
    ంబేద్కర్
    1.38
     complicaciones
    1.36
    Activations Density 0.000%

    No Known Activations