© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 196238
    Prev
    Next
    INDEX
    Explanations

    specific terms or professions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     historischen
    0.41
     históricos
    0.40
    ,__
    0.38
     humains
    0.38
     znal
    0.37
     Radiological
    0.37
     baseURL
    0.37
     Automated
    0.36
     françaises
    0.36
     त्रिज्या
    0.36
    POSITIVE LOGITS
    Breed
    0.43
    棋
    0.39
    лев
    0.38
    arrays
    0.37
    allelujah
    0.36
    entries
    0.36
     접근
    0.36
    ruit
    0.35
    anthus
    0.35
    길
    0.34
    Activations Density 0.703%

    No Known Activations