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-3-1B-IT
    3. 17-GEMMASCOPE-2-RES-16K
    4. 1150
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post
    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
    <0x8C>
    0.97
     cà
    0.77
     Kaffee
    0.77
     Edson
    0.73
    枫
    0.72
     Salford
    0.71
     গাজী
    0.71
     caffè
    0.70
     Faisal
    0.70
    <0x88>
    0.69
    POSITIVE LOGITS
    3
    1.67
     Trio
    1.62
     trio
    1.57
    三
    1.48
     Three
    1.47
     三
    1.44
    Three
    1.43
     Third
    1.41
    的三
    1.41
     Tri
    1.39
    Activations Density 3.045%

    No Known Activations