© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6117
    Prev
    Next
    INDEX
    Explanations

    Iranian and Farsi languages

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

    The neuron fires on factual, product‐oriented passages that list trade or technical specifications (e.g. export markets, item types, quantities, measurements).

    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
    녠
    1.15
    룀
    1.14
     lateribus
    1.09
    쐞
    1.05
    솎
    1.05
     exacting
    1.02
    퇸
    1.02
    끅
    1.01
    퐫
    0.99
    찧
    0.98
    POSITIVE LOGITS
     در
    1.67
     پ
    1.50
     ک
    1.45
     ن
    1.41
     ایران
    1.37
     و
    1.36
     با
    1.33
    در
    1.31
     آ
    1.30
     کار
    1.29
    Activations Density 0.058%

    No Known Activations