© 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. 31-GEMMASCOPE-2-RES-16K
    7. 6906
    Prev
    Next
    INDEX
    Explanations

    Japanese particles and symbols

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

    This neuron detects the presence of Japanese script (Kanji or Kana) 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
    鈍
    0.67
                                   
    0.64
    Entire
    0.62
    Eu
    0.61
    DCT
    0.61
    /
    0.61
    just
    0.60
    mind
    0.60
    concern
    0.59
    สุ
    0.59
    POSITIVE LOGITS
    鍖
    0.61
    </tr>
    0.61
     إِل
    0.58
     kalau
    0.57
     Screens
    0.57
    rayed
    0.57
     başvur
    0.57
     വിദ
    0.57
    ிகளும்
    0.57
     philosophie
    0.57
    Activations Density 0.005%

    No Known Activations