© 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. 86759
    Prev
    Next
    INDEX
    Explanations

    percentages, rates, or measurements

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

    The neuron activates on numerical tokens—especially measurements, percentages, and decimal numbers.

    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
     alho
    -1.51
     paño
    -1.45
    nements
    -1.45
     cykel
    -1.41
     большо
    -1.40
    chik
    -1.40
     mistura
    -1.37
     MICHAEL
    -1.37
     ग्राहक
    -1.36
    lllllll
    -1.33
    POSITIVE LOGITS
     on
    2.50
     other
    2.33
     of
    2.31
     These
    1.72
     others
    1.71
     Interestingly
    1.69
     Ironically
    1.66
     There
    1.62
     Those
    1.59
     anderen
    1.59
    Activations Density 0.108%

    No Known Activations