© 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. 102300
    Prev
    Next
    INDEX
    Explanations

    clinical and genetic testing

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

    technical content related to genetic testing, DNA analysis, and laboratory procedures.

    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
    cheque
    -1.45
     chré
    -1.32
     seemed
    -1.31
    neous
    -1.30
     seems
    -1.28
     instead
    -1.27
    ميل
    -1.27
    ֭
    -1.25
    ὴν
    -1.23
    皈
    -1.23
    POSITIVE LOGITS
    ֶּ
    1.61
    ό
    1.55
     confirmation
    1.40
     conclusive
    1.40
    endaftar
    1.38
     detalló
    1.34
     препара
    1.34
    either
    1.33
    zijn
    1.32
     مباراة
    1.32
    Activations Density 0.213%

    No Known Activations