© 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. 20630
    Prev
    Next
    INDEX
    Explanations

    Lynch surname or Lynchburg

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

    This neuron specifically activates on occurrences of the proper name “Lynch.”

    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
     剤
    -3.17
    玧
    -3.05
     歳
    -2.59
     a
    -2.56
     ""],
    -2.52
    澇
    -2.52
    瑧
    -2.45
    餿
    -2.45
    ischof
    -2.41
    .”
    -2.38
    POSITIVE LOGITS
    ’
    3.06
     stratégique
    2.69
    趼
    2.67
    𞤤
    2.56
    龌
    2.53
     "
    2.44
    ࿙
    2.42
     شما
    2.41
    毉
    2.41
     unseres
    2.38
    Activations Density 0.002%

    No Known Activations