© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 7551
    Prev
    Next
    INDEX
    Explanations

    Zi, Tzu, Ko names

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

    This neuron primarily detects the pinyin syllable “zi” (as in Chinese names or terms rendered in transliteration).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    '
    -2.27
     hodiny
    -2.14
     predomin
    -2.11
    lossians
    -2.11
    ！”
    -2.09
    or
    -2.08
    r
    -2.00
    B
    -2.00
    ”。
    -2.00
    na
    -2.00
    POSITIVE LOGITS
    
    2.78
    蚨
    2.58
     \
    2.56
     Erkenntnisse
    2.44
     \'
    2.38
     Konsequ
    2.38
     Unterstüt
    2.34
    "));
    2.34
     ก็
    2.34
    ised
    2.31
    Activations Density 0.004%

    No Known Activations