© 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. 22384
    Prev
    Next
    INDEX
    Explanations

    the surname Zhang

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

    The neuron fires on occurrences of the name “Zhang” (i.e. that Chinese surname) in the text.

    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
     That
    -3.41
    ↵
    -2.78
    that
    -2.70
    
    -2.30
     که
    -2.14
     ที่
    -2.14
    也
    -2.09
    醗
    -2.09
     army
    -2.06
    /
    -2.06
    POSITIVE LOGITS
    紧接着
    3.36
    謇
    2.78
    身边的
    2.73
     mijn
    2.47
    derdag
    2.38
    栻
    2.36
    ?",
    2.30
    𓆟
    2.30
     dedicado
    2.28
    啬
    2.28
    Activations Density 0.007%

    No Known Activations