© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 3681
    Prev
    Next
    INDEX
    Explanations

    universities and colleges

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

    The neuron detects career‐service phrases that describe someone “served as … at …” (i.e. professional appointments at institutions).

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     Saskatoon
    -1.12
     Schenectady
    -0.93
     Charlottesville
    -0.91
    Edmonton
    -0.88
     Topeka
    -0.87
     Kelowna
    -0.84
     Champaign
    -0.83
     Shreveport
    -0.83
     Spokane
    -0.80
     Medford
    -0.80
    POSITIVE LOGITS
     University
    1.86
     Saint
    1.46
    Loy
    1.42
     Hof
    1.31
     colleges
    1.29
     universities
    1.24
     Loyola
    1.24
     university
    1.24
    University
    1.21
     Mount
    1.18
    Activations Density 0.180%

    No Known Activations