© 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. 102321
    Prev
    Next
    INDEX
    Explanations

    prices and currency values

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

    The neuron is activated by numeric price expressions—sequences of digits, commas, periods and currency markers that denote monetary amounts.

    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
    </h3>
    -1.43
     that
    -1.30
     utilized
    -1.27
     formerly
    -1.20
     which
    -1.20
    僦
    -1.19
     up
    -1.19
     related
    -1.18
    romyal
    -1.18
     out
    -1.17
    POSITIVE LOGITS
    他们
    1.52
    他们的
    1.35
     exemplaire
    1.31
     skydd
    1.30
     brasileiros
    1.30
    șit
    1.28
    ᾽
    1.27
    Arbe
    1.27
    ınıza
    1.27
     nimmer
    1.26
    Activations Density 0.025%

    No Known Activations