© 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-3-12B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 730
    Prev
    Next
    INDEX
    Explanations

    place names with associated institutions

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

    This neuron activates on named geographic locations (place names).

    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
    摧
    0.50
    👛
    0.49
    🌑
    0.49
    此
    0.48
     irradi
    0.48
    字段
    0.48
     recto
    0.48
    🙄
    0.47
    怀
    0.47
    🐑
    0.47
    POSITIVE LOGITS
     County
    0.86
     City
    0.70
     Regional
    0.67
     Symphony
    0.64
     Municipal
    0.64
     University
    0.63
     Police
    0.63
     businessman
    0.63
     COUNTY
    0.62
     Chamber
    0.61
    Activations Density 0.382%

    No Known Activations