© 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. 22-GEMMASCOPE-RES-131K
    7. 69002
    Prev
    Next
    INDEX
    Explanations

    university departments and affiliations

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

    This neuron detects labels of institutional or administrative units—e.g. department, faculty, school, unit, division, district, county, company—within affiliations or geographic subdivisions.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    kiwi
    -0.96
     additional
    -0.95
    chestra
    -0.92
     '
    -0.91
     ссылке
    -0.89
     удовольствием
    -0.89
    DialogResult
    -0.88
     quedaba
    -0.87
    ''
    -0.87
     unique
    -0.86
    POSITIVE LOGITS
     of
    1.19
     maint
    1.03
    ライター
    0.93
     citazioni
    0.90
    Zdrav
    0.90
    ців
    0.88
     Кто
    0.88
     canes
    0.86
     philippe
    0.86
    mittedly
    0.86
    Activations Density 0.047%

    No Known Activations