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. 1154
    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
    "
    2.36
    (
    1.90
    )
    1.68
    -
    1.63
    :
    1.58
    .
    1.54
    ,
    1.44
    \
    1.41
    *
    1.36
    /
    1.32
    POSITIVE LOGITS
    s
    1.29
    nın
    1.07
    <unused156>
    1.07
    <unused1690>
    1.06
     ,[
    1.06
    sht
    1.04
     testaceis
    1.04
    <unused1633>
    1.03
     elytris
    1.02
    <unused848>
    1.02
    Activations Density 1.038%

    No Known Activations