© 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. 11804
    Prev
    Next
    INDEX
    Explanations

    instructional materials and programs

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

    The neuron specializes in spotting educational and instructional terminology—words referring to instruction, training, curricula, or instructional design.

    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
    waltung
    -0.78
    Explosive
    -0.76
    啕
    -0.74
    単純
    -0.73
     quen
    -0.71
     Hemisphere
    -0.71
    atriz
    -0.70
     Sax
    -0.69
     curriculum
    -0.69
    TEACHER
    -0.69
    POSITIVE LOGITS
     delivery
    1.13
    coach
    0.98
     strategies
    0.91
    Delivery
    0.89
     design
    0.89
    delivery
    0.86
    confirmed
    0.85
     Strategies
    0.82
     strategy
    0.82
    ally
    0.81
    Activations Density 0.021%

    No Known Activations