© 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. 2473
    Prev
    Next
    INDEX
    Explanations

    medical trainee and consultant roles

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

    medical professionals and specializations, particularly in academic and healthcare settings.

    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
    憊
    -0.79
    Client
    -0.75
     elemen
    -0.75
     rossa
    -0.74
    社會
    -0.73
    alleye
    -0.73
     Mohd
    -0.71
    Strap
    -0.71
    pezif
    -0.70
     STER
    -0.70
    POSITIVE LOGITS
     junior
    1.20
     trainee
    1.18
     trainees
    1.15
     registrar
    1.09
    Specialty
    1.07
     consultant
    1.05
     juniors
    1.00
    registrar
    0.98
     Consultant
    0.96
     Specialty
    0.95
    Activations Density 0.078%

    No Known Activations