© 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. 84336
    Prev
    Next
    INDEX
    Explanations

    university affiliation

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

    The neuron fires on words marking institutional affiliations or locations in descriptions of colleges and universities.

    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
    Podcast
    -0.77
    waan
    -0.76
     Podcast
    -0.72
    ghis
    -0.70
    료
    -0.68
     Pens
    -0.68
    .$_
    -0.68
    Pens
    -0.66
     interés
    -0.66
    szönöm
    -0.66
    POSITIVE LOGITS
     University
    1.67
    University
    1.51
     affili
    1.30
     UNIVERSITY
    1.19
     university
    1.17
    university
    1.14
     universities
    1.06
     affiliation
    1.05
     Universities
    1.03
     affiliated
    1.00
    Activations Density 0.031%

    No Known Activations