© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 114036
    Prev
    Next
    INDEX
    Explanations

    the name Clarke

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

    The neuron fires strongly on occurrences of the proper name “Clarke.”

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
    同样的
    -2.34
    v
    -2.25
    的角色
    -2.22
    
    -2.19
     or
    -2.17
    我没
    -2.17
    pulseira
    -2.14
    的山
    -2.13
    真的是
    -2.11
    ?!?
    -2.09
    POSITIVE LOGITS
     ก็
    2.73
    薷
    2.61
    攫
    2.48
    2.34
    Value
    2.25
    是一位
    2.23
    
    2.19
     svět
    2.16
    ons
    2.14
    !
    2.11
    Activations Density 0.002%

    No Known Activations