© 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. 9249
    Prev
    Next
    INDEX
    Explanations

    Chinese names like Zhong

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

    The neuron activates on occurrences of the Chinese name/word “Zhong” (including the character 中).

    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
    >
    -3.31
     ‘
    -2.73
    {
    -2.72
    ↵
    -2.58
     cincuenta
    -2.53
    I
    -2.53
     “
    -2.50
    ”-
    -2.48
     su
    -2.47
    -“
    -2.44
    POSITIVE LOGITS
     \_
    2.92
    是怎么回事
    2.59
    ization
    2.59
    \_\_
    2.58
    蒹
    2.52
    豨
    2.48
    ться
    2.45
    嫆
    2.44
    呓
    2.41
    ︕
    2.39
    Activations Density 0.001%

    No Known Activations