© 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. 31-GEMMASCOPE-2-RES-16K
    7. 115
    Prev
    Next
    INDEX
    Explanations

    理解语言

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

    This neuron detects non-Latin (CJK) characters or segments in the text.

    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
     esetén
    0.74
     کے
    0.68
    )،
    0.61
     և
    0.60
     ৃ
    0.60
     ⏮
    0.60
     NSUTF
    0.59
     függvény
    0.58
     یا
    0.57
     stateMutability
    0.57
    POSITIVE LOGITS
    有
    0.70
    不
    0.66
    最
    0.64
    既
    0.64
    更
    0.63
    在
    0.62
    其
    0.62
    同
    0.61
    只
    0.60
    自己
    0.60
    Activations Density 0.025%

    No Known Activations