© 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. 10899
    Prev
    Next
    INDEX
    Explanations

    closing parentheses and braces

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

    This neuron activates 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
     up
    -0.97
    mbitos
    -0.90
     partake
    -0.85
    pous
    -0.85
     to
    -0.83
    ズミ
    -0.83
    .'"
    -0.82
    Waga
    -0.81
    袤
    -0.81
    ducer
    -0.80
    POSITIVE LOGITS
     then
    1.15
     kaupung
    0.89
     imidlertid
    0.88
    كان
    0.86
    Проце
    0.85
    categoryName
    0.84
    listId
    0.82
    cuando
    0.82
    Allora
    0.82
    懾
    0.80
    Activations Density 0.003%

    No Known Activations