© 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. 59682
    Prev
    Next
    INDEX
    Explanations

    first names and surnames

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

    The neuron activates on tokens that are personal names (proper first names), regardless of script.

    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
    ଢ
    -3.17
     Their
    -3.16
    ﮦ
    -2.75
    ㊂
    -2.67
     -"
    -2.61
    现状
    -2.52
    更加
    -2.47
    
    -2.45
    ᐕ
    -2.45
     Она
    -2.45
    POSITIVE LOGITS
    .
    4.00
    the
    3.94
    姈
    3.48
    as
    3.02
    m
    2.64
     He
    2.56
    猡
    2.50
    馘
    2.44
    ли
    2.44
    야
    2.42
    Activations Density 0.006%

    No Known Activations