© 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. 109092
    Prev
    Next
    INDEX
    Explanations

    universities and studying

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

    The neuron detects mentions of educational background—words and phrases about attending school, studying a major, or enrolling in a university.

    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
     dniu
    -1.00
     cenar
    -0.87
     highschool
    -0.85
     デニム
    -0.83
     aspecto
    -0.82
     publicar
    -0.81
    glob
    -0.80
     resistir
    -0.79
    管理器
    -0.79
    lera
    -0.78
    POSITIVE LOGITS
     studying
    1.63
     studies
    1.39
     study
    1.22
    Studying
    1.22
     tanul
    1.21
     classes
    1.16
     courses
    1.14
     Studying
    1.10
    classes
    1.03
     majoring
    1.03
    Activations Density 0.049%

    No Known Activations