© 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. 42393
    Prev
    Next
    INDEX
    Explanations

    Leo followed by surname or title

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

    This neuron detects occurrences of the name “Leo.”

    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
    辚
    -3.02
    瘣
    -2.81
    就很
    -2.67
    $)$
    -2.61
    歃
    -2.59
    犴
    -2.56
    跸
    -2.55
    
    -2.53
    窠
    -2.52
    
    -2.52
    POSITIVE LOGITS
     これ
    2.77
    There
    2.70
    As
    2.61
    最初の
    2.48
    Like
    2.48
     It
    2.48
    Now
    2.38
    Unlike
    2.34
    Because
    2.34
    While
    2.34
    Activations Density 0.002%

    No Known Activations