© 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. 12521
    Prev
    Next
    INDEX
    Explanations

    Arabic and Korean script

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

    This neuron activates on non‐Latin (especially Arabic‐script) character tokens.

    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
    снов
    0.57
    closed
    0.55
    CLOSED
    0.55
    VALUE
    0.54
     basaltes
    0.54
    SEQUENCE
    0.54
    卑
    0.52
     hom
    0.52
    BUS
    0.52
    োল
    0.52
    POSITIVE LOGITS
    യു
    0.64
     Wad
    0.60
    سكر
    0.59
    아야
    0.57
     แทน
    0.56
     維
    0.56
     Yud
    0.55
     مرا
    0.54
    ਿਆਂ
    0.53
     তালিক
    0.52
    Activations Density 0.026%

    No Known Activations