© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 8472
    Prev
    Next
    INDEX
    Explanations

    Chinese, Japanese, and other languages

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

    The neuron detects individual characters from non-Latin scripts or phonetic symbol sets.

    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_24_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
    狯
    0.39
     lymphoid
    0.38
     pathophys
    0.38
     এইরূপ
    0.38
     Некоторые
    0.37
     Studies
    0.37
    Ⲇ
    0.37
     thence
    0.37
     Datenbank
    0.37
     اف
    0.36
    POSITIVE LOGITS
    能在
    0.36
    📩
    0.34
     wasn
    0.34
    这一切
    0.34
     reimb
    0.33
     mọi
    0.33
    ʻ
    0.33
    mazing
    0.33
    ศึก
    0.32
     век
    0.32
    Activations Density 0.000%

    No Known Activations