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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 48461
    Prev
    Next
    INDEX
    Explanations

    gastroenteritis or gastroenterology

    np_acts-logits-general · gemini-2.5-flash-lite

    specialized terms like wine varieties (Pinot Noir/Gris), medical conditions (gastroenteritis), or specific fields of study.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    which
    -2.33
     fazia
    -2.30
     Implemented
    -2.28
     Undoubtedly
    -2.27
     laurent
    -2.25
     moteurs
    -2.22
     Чтобы
    -2.20
    釹
    -2.20
     jokingly
    -2.20
     umożli
    -2.19
    POSITIVE LOGITS
     peculiar
    3.06
    絝
    2.80
     {
    2.73
    ⟞
    2.72
    :</
    2.72
    ୪
    2.70
     glittering
    2.67
    .}
    2.63
     teh
    2.61
    ⇿
    2.61
    Activations Density 0.008%

    No Known Activations