© 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. 13218
    Prev
    Next
    INDEX
    Explanations

    function parameters

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

    The main thing this neuron does is detect numeric literals (numbers) in the code or comments.

    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
     местных
    -1.04
     Đây
    -1.00
    IsInitialized
    -0.98
     plateado
    -0.98
     mặc
    -0.95
     soulign
    -0.93
     October
    -0.92
    ICIAS
    -0.92
     сегодняш
    -0.91
     осен
    -0.91
    POSITIVE LOGITS
    udur
    1.03
     offering
    1.02
     what
    1.00
     ότι
    0.99
     Offering
    0.96
    yskland
    0.95
     свою
    0.93
     ArrayAdapter
    0.92
     Tomé
    0.92
    俱
    0.92
    Activations Density 0.031%

    No Known Activations