© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 84433
    Prev
    Next
    INDEX
    Explanations

    East Asian surnames

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

    This neuron specializes in spotting numeric and parenthetical metadata in biographical or factual text (e.g., years, dates, and numbers enclosed in parentheses).

    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
    龔
    -0.92
     lingerie
    -0.88
     Econ
    -0.86
    Guang
    -0.84
     APR
    -0.81
     Zij
    -0.81
     Dae
    -0.80
     Advoc
    -0.80
    ECAUSE
    -0.79
     tiara
    -0.78
    POSITIVE LOGITS
     Zhang
    1.55
     Liu
    1.52
     Chen
    1.50
     Lee
    1.34
     Li
    1.23
     Wang
    1.22
     Zhou
    1.20
     Sun
    1.17
     Huang
    1.16
     Kim
    1.13
    Activations Density 0.036%

    No Known Activations