© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 128883
    Prev
    Next
    INDEX
    Explanations

    This neuron fires on numeric and monetary expressions (numbers, dollar signs, percentages, discounts) indicating pricing or quantitative details.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    items for sale

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     quando
    -0.86
     procedure
    -0.85
     primeira
    -0.84
     common
    -0.83
     preparation
    -0.82
     first
    -0.81
     Anhang
    -0.81
     wichtigsten
    -0.80
     relationship
    -0.79
    dermal
    -0.78
    POSITIVE LOGITS
     eBay
    1.22
     yüzde
    1.15
    こちらの
    1.02
     LoginComponent
    1.02
     priced
    1.02
     auction
    1.01
    lüğü
    1.01
     MessageType
    0.99
     ditawarkan
    0.98
    Offered
    0.98
    Activations Density 0.060%

    No Known Activations