© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 6946
    Prev
    Next
    INDEX
    Explanations

    medical patient data and outcomes

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

    medical and scientific content related to clinical studies, procedures, and patient treatments.

    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
    aster
    -0.88
     horri
    -0.85
    (_.
    -0.85
     obligé
    -0.85
    nings
    -0.82
    蛀
    -0.81
    uchte
    -0.81
     Maur
    -0.81
     المه
    -0.81
    ͻ
    -0.80
    POSITIVE LOGITS
    ૬
    1.00
     patients
    0.93
     להשת
    0.88
    เด็ก
    0.87
    crowd
    0.85
    》,
    0.85
    ดัง
    0.84
     objectively
    0.84
     showing
    0.84
     obvious
    0.82
    Activations Density 0.601%

    No Known Activations