© 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. 32147
    Prev
    Next
    INDEX
    Explanations

    educational worksheets and materials

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

    The neuron fires on words that signal educational or assessment contexts—terms like test, review, practice, worksheet, students, questions, and related instructional vocabulary.

    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
    matics
    -0.77
    fej
    -0.77
    ogenous
    -0.75
    tora
    -0.75
    imply
    -0.75
    ționale
    -0.75
    
    -0.71
    blockchain
    -0.71
    aned
    -0.71
    Variance
    -0.70
    POSITIVE LOGITS
     worksheet
    1.34
     worksheets
    1.04
     foldable
    0.98
     notes
    0.96
    Worksheet
    0.93
     stations
    0.90
     organizer
    0.90
    worksheet
    0.89
     handout
    0.86
     Stations
    0.86
    Activations Density 0.016%

    No Known Activations