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. 101
    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
    ,
    2.71
    ،
    2.00
    、
    1.85
    ,
    1.68
    :
    1.52
    -,
    1.43
    .,
    1.29
    ;
    1.27
    .
    1.22
     ،
    1.20
    POSITIVE LOGITS
     including
    1.66
     although
    1.59
     albeit
    1.56
     consisting
    1.52
     namely
    1.52
     though
    1.52
     especially
    1.51
     culminating
    1.51
     which
    1.47
     particularly
    1.47
    Activations Density 2.502%

    No Known Activations