© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 64007
    Prev
    Next
    INDEX
    Explanations

    medical professions and surgical contexts

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

    abbreviations and identifiers related to medical organizations and institutions, like hospitals, medical corporations, and healthcare systems.

    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
     Psychol
    -1.08
     lycée
    -1.06
     PSYCH
    -1.04
     pernic
    -0.96
     entreprises
    -0.94
     PREG
    -0.93
     GUARANTE
    -0.92
     Psychological
    -0.90
     Astrophysics
    -0.90
     cryptographic
    -0.90
    POSITIVE LOGITS
     medical
    3.84
     patients
    3.61
     hospital
    3.42
     healthcare
    3.38
     patient
    3.16
     doctors
    3.14
     hospitals
    3.05
     Medical
    2.95
     Patients
    2.92
     health
    2.86
    Activations Density 0.489%

    No Known Activations