© 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. 10-GEMMASCOPE-RES-131K
    7. 3870
    Prev
    Next
    INDEX
    Explanations

    Vicki or Nico

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

    The neuron detects the specific personal names “Nico” and “Vicki.”

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
     Giving
    -2.47
    ные
    -2.45
     How
    -2.33
    舠
    -2.31
    “
    -2.31
    LVANIA
    -2.27
    u
    -2.27
    趼
    -2.25
    
    -2.23
     Which
    -2.17
    POSITIVE LOGITS
    ﮕ
    3.09
    ܆
    2.81
    那我
    2.53
    ↵↵
    2.39
    ꦢ
    2.34
    蕷
    2.33
    a
    2.30
     моя
    2.30
     мои
    2.28
    
    2.28
    Activations Density 0.001%

    No Known Activations