© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 12739
    Prev
    Next
    INDEX
    Explanations

    education and schooling

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

    This neuron fires on capitalized institutional or program names and formal proper nouns (e.g., “UNESCO,” “Education,” “Common Core,” “Sustainable Development”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_31_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    dbThoughtData
    0.55
     поча
    0.54
    workouts
    0.54
     Prabh
    0.54
    ர்ந்து
    0.53
    ப்த
    0.52
    开拓
    0.52
    螨
    0.51
     Joseph
    0.50
     अत्या
    0.50
    POSITIVE LOGITS
    UNESCO
    1.74
     UNESCO
    1.73
     Unesco
    1.59
    Education
    1.39
     Education
    1.38
    Educational
    1.34
     education
    1.33
     Educational
    1.31
    education
    1.31
    educational
    1.26
    Activations Density 0.143%

    No Known Activations