© 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. 34-GEMMASCOPE-RES-131K
    7. 32634
    Prev
    Next
    INDEX
    Explanations

    Chinese surnames and given names

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

    This neuron detects the names of parties (plaintiff or appellant names) in legal case citations.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    烨
    -1.09
    越南
    -0.98
    琨
    -0.97
    珏
    -0.94
    钰
    -0.87
    玮
    -0.86
    晔
    -0.83
    vrouw
    -0.82
     quidem
    -0.82
    蓁
    -0.82
    POSITIVE LOGITS
     Li
    1.52
     Wang
    1.42
     Zhang
    1.38
     Chen
    1.36
     Sun
    1.26
    wen
    1.16
     Song
    1.13
    Li
    1.12
     Shi
    1.12
    Q
    1.11
    Activations Density 0.072%

    No Known Activations