© 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. 22-GEMMASCOPE-RES-131K
    7. 67687
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or percentages

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

    The neuron strongly activates on numeric data tokens—numbers, percentages, and other quantitative measurements.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    œuf
    -0.93
    啲
    -0.93
    gefahr
    -0.84
    ומרים
    -0.83
    த்
    -0.80
     nytt
    -0.79
    FOREIGN
    -0.79
     чувства
    -0.77
     eigenen
    -0.77
     declining
    -0.76
    POSITIVE LOGITS
    ্ন
    0.91
    ̉
    0.90
    PointerException
    0.90
    ifornie
    0.90
     الاجتماعية
    0.90
    vencia
    0.89
     LIABLE
    0.86
    iredo
    0.85
     közül
    0.83
    isNull
    0.83
    Activations Density 0.057%

    No Known Activations