© 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. 24-GEMMASCOPE-2-RES-16K
    7. 9872
    Prev
    Next
    INDEX
    Explanations

    Iran, China, Russia

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

    The neuron strongly activates on mentions of the country name “Iran” (and its adjectival form “Iranian”).

    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
    ↵
    0.89
    1
    0.87
    0
    0.84
     berth
    0.79
    I
    0.77
    ↵↵
    0.75
     (
    0.75
    (?)
    0.75
    8
    0.75
     arbit
    0.73
    POSITIVE LOGITS
    тың
    0.96
    ان
    0.92
     化学
    0.91
     হাসানের
    0.90
    न
    0.88
     государственной
    0.86
    ólicos
    0.86
    acaktır
    0.86
     정책
    0.86
    нутри
    0.84
    Activations Density 0.003%

    No Known Activations