© 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. 118270
    Prev
    Next
    INDEX
    Explanations

    don names

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

    the neuron detects personal names beginning with the substring “Don” (e.g. Don-ohue, Don-aghe, Dona).

    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
    线上
    -0.97
    食器
    -0.85
     wayward
    -0.80
     thoughtless
    -0.78
     recuer
    -0.76
    ELING
    -0.76
     maquiagem
    -0.76
    shima
    -0.76
    bilité
    -0.75
    eling
    -0.75
    POSITIVE LOGITS
    之所以
    0.77
     SECON
    0.73
     nobis
    0.71
    LLY
    0.69
    Mare
    0.69
     cbs
    0.67
    scry
    0.67
    Southeast
    0.66
    相片
    0.66
     sevi
    0.66
    Activations Density 0.016%

    No Known Activations