© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 10926
    Prev
    Next
    INDEX
    Explanations

    Liu, Lui, 柳 names

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

    The neuron fires strongly on occurrences of the surname “Liu” (i.e. proper-name mentions of Liu).

    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
    0
    -3.45
     这个
    -3.14
    ."
    -3.11
    ;
    -3.03
    R
    -2.91
    ’
    -2.59
    ,”
    -2.59
    A
    -2.58
    T
    -2.56
     for
    -2.48
    POSITIVE LOGITS
     ſou
    3.45
    
    3.25
     seront
    3.25
    嫆
    3.19
     asisten
    3.11
    畊
    3.03
     crée
    2.97
     ſy
    2.95
    薷
    2.94
     faites
    2.83
    Activations Density 0.005%

    No Known Activations