© 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. 10021
    Prev
    Next
    INDEX
    Explanations

    Alaska, arctic, Aurora

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

    The main thing this neuron does is detect mentions of geographic 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
     কুমিল্লা
    0.76
     پنجاب
    0.63
    Provence
    0.61
    Atlanta
    0.60
    滏
    0.60
     Murcia
    0.59
    Pune
    0.59
    沂
    0.57
    राष्ट्र
    0.57
    ྪ
    0.57
    POSITIVE LOGITS
     Alaska
    2.23
    Alaska
    2.13
     Alaskan
    2.13
     Arctic
    1.94
    Arctic
    1.84
     arctic
    1.82
     tundra
    1.75
    arctic
    1.66
     Anchorage
    1.63
     Inuit
    1.60
    Activations Density 0.243%

    No Known Activations