© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5651
    Prev
    Next
    INDEX
    Explanations

    locations and technologies

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

    The neuron flags specific place names (countries, states, cities, etc.).

    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
    苳
    0.56
    ophagy
    0.52
    ემის
    0.52
    洹
    0.51
     नामक
    0.49
    :[
    0.49
    |+|
    0.48
    []}
    0.47
    Ở
    0.47
     遊ん
    0.47
    POSITIVE LOGITS
     disagrees
    0.52
     gelecek
    0.52
     খুশি
    0.51
     merasa
    0.50
    を迎
    0.50
    uas
    0.49
     Misalnya
    0.49
    覺得
    0.49
     যোগ্যতা
    0.49
     ($
    0.48
    Activations Density 0.013%

    No Known Activations