© 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. 69490
    Prev
    Next
    INDEX
    Explanations

    martin followed by names or initials

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

    The neuron consistently activates on occurrences of the proper name “Martin.”

    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
     unſ
    -3.06
     позволя
    -2.75
    
    -2.64
    蹰
    -2.44
    ев
    -2.36
     представителей
    -2.36
    
    -2.34
    ↵
    -2.34
     incred
    -2.31
    ^{+}\
    -2.25
    POSITIVE LOGITS
    ization
    2.97
    ～　
    2.97
    What
    2.94
    Many
    2.88
    Even
    2.86
    Nearly
    2.83
    During
    2.77
    Just
    2.77
    Although
    2.73
    Since
    2.72
    Activations Density 0.006%

    No Known Activations