© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 1097
    Prev
    Next
    INDEX
    Explanations

    college and learner support

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

    This neuron detects proper-name tokens, especially title-cased institution or place names.

    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
     языку
    -0.82
    儿童
    -0.82
     GRADUATE
    -0.81
     书
    -0.76
    getObject
    -0.76
     unknownFields
    -0.71
    ₺
    -0.71
    entraî
    -0.71
    HB
    -0.70
     doctoral
    -0.70
    POSITIVE LOGITS
     college
    1.45
     learner
    1.45
     learners
    1.26
     colleges
    1.17
    college
    1.05
     employer
    1.03
     COLLEGE
    1.03
     College
    1.03
     vocational
    1.00
     automotive
    1.00
    Activations Density 0.016%

    No Known Activations