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. 534
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    gg-gs/gemma-scope-2-1b-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
    :
    1.57
     And
    1.34
     and
    1.31
    And
    1.21
    and
    1.18
    ;
    1.18
    It
    1.15
    A
    1.15
     :
    1.14
    But
    1.09
    POSITIVE LOGITS
     whatnot
    1.87
     ultimately
    1.82
    <unused73>
    1.79
     consequently
    1.78
     oftentimes
    1.73
    <unused599>
    1.70
     therefor
    1.70
     subsequently
    1.66
     hopefully
    1.64
     tiež
    1.64
    Activations Density 2.984%

    No Known Activations