© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 50278
    Prev
    Next
    INDEX
    Explanations

    of medical departments

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

    academic or medical department affiliations within institutions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates strongly on sections describing academic credentials, medical degrees, training positions, and institutional affiliations in a CV‐style biography.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
    ğını
    -0.86
    🐟
    -0.84
    മാ
    -0.82
     Dentist
    -0.78
     クリニック
    -0.77
     controladores
    -0.75
    inio
    -0.75
     ABN
    -0.74
     terbuat
    -0.73
     Lieben
    -0.73
    POSITIVE LOGITS
     Internal
    1.21
     internal
    1.09
     surgery
    1.03
     emergency
    0.96
    Internal
    0.94
     Surgery
    0.90
    internal
    0.90
     department
    0.90
     Department
    0.89
     Family
    0.86
    Activations Density 0.048%

    No Known Activations