© 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. 10080
    Prev
    Next
    INDEX
    Explanations

    island or isolation

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

    This neuron spotlights mentions of geographic islands or place names containing “Island.”

    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
    akura
    0.61
     লী
    0.59
     ক
    0.58
    aket
    0.55
     अभ्यर्थियों
    0.54
    ะไร
    0.53
    ج
    0.52
    rifle
    0.52
     EPO
    0.52
    夊
    0.52
    POSITIVE LOGITS
    屿
    0.92
    嶼
    0.76
    но
    0.58
    ма
    0.57
     phút
    0.57
    āju
    0.57
    izmus
    0.56
    Rail
    0.55
    מין
    0.55
     thiếu
    0.54
    Activations Density 0.192%

    No Known Activations