© 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. 65652
    Prev
    Next
    INDEX
    Explanations

    javascript code syntax

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

    This neuron fires on number literals (numeric tokens) in the 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_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
     telle
    -1.05
     位置
    -0.83
    Kann
    -0.81
     kompetisi
    -0.79
     Elekt
    -0.79
     Nylon
    -0.79
    bezpiecz
    -0.78
     artig
    -0.77
    Chir
    -0.77
     захворю
    -0.75
    POSITIVE LOGITS
     console
    1.70
    console
    1.59
    const
    1.21
     process
    1.07
     const
    1.01
     return
    1.00
    γραφία
    0.90
     document
    0.89
     Promise
    0.89
     restricciones
    0.85
    Activations Density 0.006%

    No Known Activations