© 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. 76132
    Prev
    Next
    INDEX
    Explanations

    names and places

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

    This neuron activates on occurrences of the character sequence “yuan,” matching that exact token or substring in various contexts.

    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
    CreateMap
    -0.89
    自己是
    -0.82
     gemüt
    -0.80
    schuhe
    -0.78
    
    -0.75
    般的
    -0.73
    karte
    -0.73
     Тро
    -0.71
     محفوظ
    -0.71
    MAJ
    -0.70
    POSITIVE LOGITS
    件
    0.83
    ushing
    0.81
     túnel
    0.80
    此
    0.79
     prinsip
    0.79
    苳
    0.79
     mesmo
    0.79
    ΡΟ
    0.78
     redenen
    0.78
    婴
    0.77
    Activations Density 0.011%

    No Known Activations