© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 9555
    Prev
    Next
    INDEX
    Explanations

    monetary values and prices

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

    This neuron activates on numeric tokens—digits and numbers (including decimals)—typically capturing quantities, prices, dates, or other numeric values.

    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
    ynchronously
    -1.53
     your
    -1.30
     músculo
    -1.26
     identificação
    -1.26
     descart
    -1.25
     educativos
    -1.24
    讓你
    -1.23
     Möglichkeit
    -1.22
    让你
    -1.21
     fabricants
    -1.21
    POSITIVE LOGITS
     to
    1.87
     a
    1.75
     for
    1.55
     of
    1.41
     todella
    1.41
    ="
    1.34
    怎么可能
    1.32
     samfun
    1.31
     damaligen
    1.29
     or
    1.27
    Activations Density 0.048%

    No Known Activations