© 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. 10-GEMMASCOPE-RES-131K
    7. 110990
    Prev
    Next
    INDEX
    Explanations

    closing punctuation and delimiters

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

    The neuron detects numeric literals (sequences of digits, including numbers in code or data).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    そういえば
    -2.38
     Atención
    -2.31
    逐渐
    -2.31
     Fakta
    -2.11
    archiwizowane
    -2.11
    うーん
    -2.06
     individuelles
    -1.97
    呿
    -1.95
     {
    -1.95
    曖昧さ
    -1.95
    POSITIVE LOGITS
    \
    2.03
     because
    1.92
     tucked
    1.79
     due
    1.75
     extending
    1.71
     there
    1.69
     but
    1.68
     when
    1.62
     until
    1.62
     putting
    1.59
    Activations Density 0.011%

    No Known Activations