© 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. 119393
    Prev
    Next
    INDEX
    Explanations

    clinical research and medical news

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

    headers, citations, and formatting elements in medical or scientific publications.

    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
     screenings
    -0.80
    -\
    -0.79
    ziehungs
    -0.75
    ս
    -0.73
    iological
    -0.72
     غ
    -0.72
     kann
    -0.72
     iban
    -0.72
    WIN
    -0.71
    ionale
    -0.71
    POSITIVE LOGITS
    Meds
    1.23
    ktır
    0.85
    Disclosures
    0.79
     damska
    0.77
    TableId
    0.76
    vira
    0.76
    >",
    0.75
     oiseaux
    0.75
    peri
    0.75
    lampu
    0.75
    Activations Density 0.019%

    No Known Activations