© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 30217
    Prev
    Next
    INDEX
    Explanations

    hospital departments and consultations

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

    medical or healthcare settings such as hospitals, emergency departments, and clinics.

    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
     Sekolah
    -0.88
     pharmacists
    -0.83
     schools
    -0.78
     FREDERICK
    -0.77
     Jenis
    -0.77
     WELD
    -0.77
     Scuola
    -0.76
    Santé
    -0.75
    mimetype
    -0.74
     bijou
    -0.73
    POSITIVE LOGITS
     Consult
    1.29
     consultations
    1.20
     consult
    1.17
     consultation
    1.00
     consulted
    0.95
    Consult
    0.95
    consult
    0.94
     unidad
    0.93
     unit
    0.92
     consultas
    0.90
    Activations Density 0.112%

    No Known Activations