© 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. 34-GEMMASCOPE-RES-131K
    7. 109205
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

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

    The neuron is specialized to pick out long multi-digit numerical strings—especially four-digit years and volume/page numbers used in legal case citations.

    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
    צי
    -0.79
     ninety
    -0.76
    zeich
    -0.72
    ascii
    -0.71
    rów
    -0.71
     éste
    -0.70
    ommen
    -0.69
    enberg
    -0.69
    isher
    -0.68
     twenty
    -0.67
    POSITIVE LOGITS
     weeks
    0.90
     week
    0.90
     days
    0.83
    Switcher
    0.81
    weeks
    0.79
    Weeks
    0.78
    Suggestions
    0.76
     months
    0.76
    WEEK
    0.76
    Years
    0.75
    Activations Density 0.247%

    No Known Activations