© 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. 107801
    Prev
    Next
    INDEX
    Explanations

    school and grade related terms

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

    The main thing this neuron does is find mentions of school and grade-level educational contexts.

    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
     undergraduate
    -0.98
    College
    -0.88
    college
    -0.84
     College
    -0.82
    COLLEGE
    -0.78
    大學
    -0.77
    êté
    -0.77
    ComponentModel
    -0.73
     fatigu
    -0.73
     undergraduates
    -0.72
    POSITIVE LOGITS
     recess
    1.41
     class
    1.29
     cafeteria
    1.17
     lunch
    1.02
     lockers
    1.00
    teacher
    1.00
     PROJECTS
    0.99
     PTO
    0.99
    lunch
    0.98
     assembly
    0.98
    Activations Density 0.053%

    No Known Activations