© 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. 454
    Prev
    Next
    INDEX
    Explanations

    numbers, dates, and punctuation

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

    The neuron fires strongly on very high‐frequency, “boilerplate” tokens—common words, punctuation, and metadata elements that appear across virtually every article (e.g. “the,” commas, dateline bits, etc.).

    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
     COVID
    -2.72
     covid
    -2.72
     Covid
    -2.67
     pandemic
    -2.64
    COVID
    -2.47
    covid
    -2.41
     ২০
    -2.38
    Covid
    -2.36
     TikTok
    -2.16
     metaverse
    -2.11
    POSITIVE LOGITS
     ২০১
    1.89
     ۲۰۱
    1.75
     http
    1.64
     Ebola
    1.55
    glyphicon
    1.53
     Huffington
    1.50
     xrange
    1.37
     ISIS
    1.28
     Zika
    1.25
     ‪
    1.24
    Activations Density 0.296%

    No Known Activations