© 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. 103229
    Prev
    Next
    INDEX
    Explanations

    Fight Card

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

    This neuron detects numeric tokens and quantifiable information—digits, figures, dates, counts, and other number-like elements.

    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
    Quoted
    -0.88
     quote
    -0.84
    Quote
    -0.79
     Quoted
    -0.79
     Quotes
    -0.79
     AZ
    -0.79
     Cairns
    -0.77
    quoted
    -0.77
    quote
    -0.77
    packing
    -0.77
    POSITIVE LOGITS
    temon
    0.89
     chin
    0.80
    olkien
    0.73
    Chin
    0.73
     finalized
    0.72
    쳤
    0.72
    CHIN
    0.69
    Cli
    0.69
     lombok
    0.69
    chin
    0.68
    Activations Density 0.014%

    No Known Activations