© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 65272
    Prev
    Next
    INDEX
    Explanations

    roman numeral II

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

    The neuron activates on occurrences of the token “II” (the Roman numeral or sectional marker “II”).

    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
    ください
    -0.93
     cutting
    -0.79
     ostensibly
    -0.78
    立法
    -0.75
     financial
    -0.73
    occuper
    -0.72
     old
    -0.72
     resta
    -0.71
    先日
    -0.71
     прихо
    -0.70
    POSITIVE LOGITS
     iii
    1.05
    III
    0.87
    umin
    0.86
    
    0.85
     Topical
    0.84
    quickly
    0.84
     SHEET
    0.83
    maintain
    0.82
     verla
    0.82
    ющихся
    0.81
    Activations Density 0.035%

    No Known Activations