© 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
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 28144
    Prev
    Next
    INDEX
    Explanations

    programming keywords and identifiers

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

    The neuron fires on standalone numeric literals (numbers) in code snippets.

    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
     zudem
    -0.88
     dropper
    -0.88
    accor
    -0.87
     which
    -0.86
     at
    -0.85
    ͺ
    -0.85
     HEAVEN
    -0.84
    apnews
    -0.82
    Якщо
    -0.82
     while
    -0.82
    POSITIVE LOGITS
     noël
    0.91
     slår
    0.90
     gammel
    0.81
     slutt
    0.81
     menim
    0.81
    nics
    0.80
     balans
    0.79
    Well
    0.78
     vilja
    0.77
     Lucia
    0.77
    Activations Density 0.008%

    No Known Activations