© 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. 99949
    Prev
    Next
    INDEX
    Explanations

    Maurice, Mauritius, Maury

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

    The neuron consistently activates on the proper name “Maurice.”

    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
    ндарт
    -3.03
     cittadino
    -3.00
    赑
    -2.91
    侂
    -2.80
    著名的
    -2.73
    
    -2.70
    廔
    -2.70
    偁
    -2.67
    毉
    -2.67
    嘤
    -2.67
    POSITIVE LOGITS
    and
    3.39
    a
    2.97
     he
    2.81
    ことがあります
    2.73
    椟
    2.70
    祤
    2.50
    
    2.45
    摭
    2.42
    頷
    2.38
    ли
    2.36
    Activations Density 0.007%

    No Known Activations