© 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. 10040
    Prev
    Next
    INDEX
    Explanations

    Wayne and following names

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

    The neuron selectively activates on the proper name “Wayne.”

    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
    猡
    -3.17
    )$
    -3.16
    韞
    -2.95
    揼
    -2.83
    "}}>
    -2.77
    狁
    -2.69
    0
    -2.67
    ”，
    -2.64
    ⡯
    -2.61
    ).
    -2.56
    POSITIVE LOGITS
    )
    3.28
    蹂
    2.77
     Until
    2.70
     baik
    2.63
     However
    2.55
    ваясь
    2.47
    ют
    2.34
    鵟
    2.33
     Мы
    2.31
    Según
    2.30
    Activations Density 0.003%

    No Known Activations