© 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. 95489
    Prev
    Next
    INDEX
    Explanations

    code snippet delimiters

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

    The neuron fires primarily on numeric literals (digits) in code.

    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
     Processors
    -0.77
     Coli
    -0.76
     etc
    -0.76
     opět
    -0.76
     collectivités
    -0.75
    름
    -0.75
     gói
    -0.73
    又在
    -0.73
    etron
    -0.72
     کردند
    -0.72
    POSITIVE LOGITS
     digo
    1.00
    efficiency
    0.84
     Sharp
    0.84
     вентиля
    0.83
    莢
    0.82
     Mund
    0.82
    nischen
    0.81
     bisa
    0.81
     licenci
    0.80
     gaya
    0.79
    Activations Density 0.002%

    No Known Activations