© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65073
    Prev
    Next
    INDEX
    Explanations

    medical school united states

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

    titles and professional credentials such as Doctor, MD, and other medical or academic affiliations.

    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
     alimony
    -0.82
    dafx
    -0.79
    thora
    -0.79
     ۱۳
    -0.77
    гант
    -0.75
    training
    -0.74
     Thurman
    -0.73
    reide
    -0.72
    患者
    -0.71
    izophrenia
    -0.71
    POSITIVE LOGITS
     health
    2.06
     medical
    1.89
     infir
    1.72
     nurse
    1.68
     Health
    1.66
    health
    1.50
    Health
    1.48
     healthcare
    1.44
     clinic
    1.44
     HEALTH
    1.34
    Activations Density 0.034%

    No Known Activations