© 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. 22-GEMMASCOPE-RES-131K
    7. 74941
    Prev
    Next
    INDEX
    Explanations

    rinary health

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

    numerical values in text, particularly years, dates, and numbers.

    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_22/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
    Краси
    -1.05
     якості
    -0.98
    最近
    -0.98
     навіть
    -0.97
     появится
    -0.97
    Осно
    -0.94
    Сегодня
    -0.94
     např
    -0.93
     дії
    -0.93
    Ранее
    -0.93
    POSITIVE LOGITS
     what
    1.07
    $.
    1.03
     przede
    1.02
    ={
    0.96
     befür
    0.96
    抿
    0.96
     colchón
    0.94
     grueso
    0.94
     denominado
    0.94
    cortina
    0.93
    Activations Density 0.251%

    No Known Activations