© 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. 13126
    Prev
    Next
    INDEX
    Explanations

    programming language syntax

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

    This neuron fires on numeric literals or tokens representing numbers (e.g., integer constants or numeric strings) 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
    ʻ
    -1.21
     piaci
    -1.13
     orale
    -1.10
    **
    -1.04
     siè
    -1.02
     ？
    -1.02
     activités
    -1.01
    zten
    -1.00
     kompatibel
    -1.00
    來到
    -0.99
    POSITIVE LOGITS
     no
    1.00
     it
    0.99
     to
    0.99
     followed
    0.97
     verurs
    0.96
     ಪ
    0.94
     then
    0.93
     doesn
    0.89
     how
    0.87
     where
    0.87
    Activations Density 0.007%

    No Known Activations