© 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. 34-GEMMASCOPE-RES-131K
    7. 83011
    Prev
    Next
    INDEX
    Explanations

    kallikrein or names starting with kal

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

    names or words from South Asian and Eastern European languages.

    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_34/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
    رحلة
    -0.77
     appeared
    -0.71
    ocera
    -0.71
    するための
    -0.70
    wenye
    -0.69
    僖
    -0.68
    なー
    -0.68
     dahin
    -0.68
     Medley
    -0.68
    صاب
    -0.67
    POSITIVE LOGITS
    ʇ
    0.80
     Otago
    0.79
     заку
    0.75
     savoury
    0.73
     Kall
    0.72
    왕
    0.71
    ƀ
    0.71
    ozo
    0.70
     Moms
    0.69
     języka
    0.69
    Activations Density 0.017%

    No Known Activations