© 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. 24-GEMMASCOPE-2-RES-16K
    7. 3631
    Prev
    Next
    INDEX
    Explanations

    country of origin or manufacturer

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

    The neuron fires on tokens naming geographic origins or locations (e.g., country or region 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_24_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
    ्स
    0.72
    طر
    0.68
     যাতে
    0.68
    Erro
    0.65
     შედ
    0.64
     NodeJS
    0.64
    ске
    0.64
    ᗜ
    0.63
    сить
    0.63
     جانب
    0.61
    POSITIVE LOGITS
     proiz
    0.68
     pourquoi
    0.68
     uye
    0.65
     χώρα
    0.64
     county
    0.64
     departs
    0.64
     responded
    0.63
    דינה
    0.63
     égaux
    0.63
     reaffirmed
    0.62
    Activations Density 0.001%

    No Known Activations