© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46918
    Prev
    Next
    INDEX
    Explanations

    modest, grand, intricate

    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/layer_31_width_262k_l0_medium
    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
     dumpfile
    0.45
    惰
    0.42
     hablaremos
    0.41
     วิชา
    0.41
    Vocabulary
    0.40
     ľudí
    0.39
     อื่น
    0.39
    ﹙
    0.39
    ла
    0.39
    ächlich
    0.39
    POSITIVE LOGITS
     daffodils
    0.45
     an
    0.44
     ap
    0.44
     Lloyds
    0.44
     brews
    0.43
    க்
    0.43
    ies
    0.43
     t
    0.42
     agonist
    0.41
     Ã
    0.41
    Activations Density 0.003%

    No Known Activations