© 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. 41648
    Prev
    Next
    INDEX
    Explanations

    years, numbers, and lists

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

    The neuron selectively activates on numeric tokens (years, percentages, counts, and other digit sequences) in the text.

    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
     to
    -2.75
     When
    -2.67
     as
    -2.59
     more
    -2.31
     by
    -2.31
     for
    -2.31
     before
    -2.30
     while
    -2.14
     if
    -2.11
     after
    -2.05
    POSITIVE LOGITS
     varmt
    2.09
    '
    1.97
     naszej
    1.92
     flyg
    1.90
     rosario
    1.90
    泐
    1.87
    m
    1.87
     cykel
    1.85
    ński
    1.84
    l
    1.80
    Activations Density 0.073%

    No Known Activations