Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-4B-IT
    3. 22-GEMMASCOPE-2-RES-65K
    4. 3377
    Prev
    Next
    INDEX
    Explanations

    `9` followed by digits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     péri
    0.94
     regard
    0.86
     bataille
    0.86
    搠
    0.86
     lâ
    0.84
    десят
    0.82
     falla
    0.82
     ideia
    0.81
     carbides
    0.81
     testigos
    0.80
    POSITIVE LOGITS
    ый
    0.98
     việc
    0.88
    んだ
    0.85
    ης
    0.84
    czyny
    0.83
    så
    0.82
    schw
    0.82
    тся
    0.81
     बांटा
    0.81
    我
    0.81
    Activations Density 0.018%

    No Known Activations