© 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. 66354
    Prev
    Next
    INDEX
    Explanations

    proper names and places

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

    This neuron detects tokens beginning with the letters “Ja” (case-sensitive).

    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
    出现在
    -0.87
     gou
    -0.81
    间
    -0.79
    JoinColumn
    -0.78
    ErrUnexpected
    -0.78
    表达
    -0.76
    (((
    -0.76
    考试
    -0.75
     initialise
    -0.75
    _;
    -0.74
    POSITIVE LOGITS
     sinner
    0.82
     Já
    0.76
     occhi
    0.75
    postData
    0.75
     Моло
    0.74
    rainy
    0.73
    cartier
    0.71
    人には
    0.71
    altro
    0.70
    audrait
    0.70
    Activations Density 0.029%

    No Known Activations