© 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. 39109
    Prev
    Next
    INDEX
    Explanations

    VI Roman numeral sequences

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

    The neuron detects occurrences of the Roman numeral “VI.”

    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
    ↵↵
    -3.36
     «
    -2.61
     ‘‘
    -2.53
    
    -2.50
    '
    -2.42
     лучший
    -2.31
     наши
    -2.25
    杙
    -2.23
    :
    -2.22
    —
    -2.22
    POSITIVE LOGITS
     It
    2.78
    ?"
    2.72
    ⢊
    2.63
    蹰
    2.61
    鹇
    2.56
     الأخرى
    2.52
    ния
    2.45
     was
    2.38
     averiguar
    2.38
    횃
    2.36
    Activations Density 0.003%

    No Known Activations