© 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. 9566
    Prev
    Next
    INDEX
    Explanations

    keywords and code terms

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

    The neuron fires on numeric literals (numbers) in the text.

    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
     all
    -1.15
     considerably
    -1.08
     several
    -1.05
    ridescent
    -1.04
     for
    -1.03
     in
    -0.96
     numerous
    -0.96
     quick
    -0.95
     quite
    -0.95
     probably
    -0.94
    POSITIVE LOGITS
     minum
    1.02
     ܘ
    0.99
    のだろう
    0.97
     évalu
    0.95
     véhic
    0.90
     améli
    0.90
     座
    0.86
     lauded
    0.84
     alimentare
    0.84
     distinguer
    0.84
    Activations Density 0.071%

    No Known Activations