© 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. 37836
    Prev
    Next
    INDEX
    Explanations

    medical departments and experts

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

    names of medical institutions and hospitals in scientific papers.

    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
     veterin
    -0.84
     lycée
    -0.81
    (_.
    -0.80
     çi
    -0.77
     NURS
    -0.76
     Pizzeria
    -0.75
     Archiproducts
    -0.75
     QUIZ
    -0.75
    {.
    -0.75
     animé
    -0.74
    POSITIVE LOGITS
     department
    1.15
     outpatient
    1.13
     departments
    1.13
     ward
    1.05
     экспер
    1.05
     Department
    1.04
     Departments
    1.03
     expert
    0.98
     Expert
    0.96
    Department
    0.96
    Activations Density 0.049%

    No Known Activations