© 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. 2082
    Prev
    Next
    INDEX
    Explanations

    中文 compound words

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

    The neuron flags sequences of Chinese characters.

    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
     Mereka
    1.64
     ⏮
    1.62
     mivel
    1.58
     🥰
    1.56
     නමුත්
    1.53
     අඩු
    1.53
     ennek
    1.53
     comprimento
    1.52
     ETFs
    1.51
     Portanto
    1.51
    POSITIVE LOGITS
    大
    1.66
    、
    1.62
    地
    1.52
    的
    1.50
    有
    1.48
    空
    1.48
    之
    1.47
    化
    1.45
    一
    1.45
    可
    1.43
    Activations Density 0.024%

    No Known Activations