© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 66367
    Prev
    Next
    INDEX
    Explanations

    number of copies sold

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

    The neuron activates on numerical and quantitative tokens—dates, figures, chart positions, sales numbers, etc.—i.e. passages conveying statistics.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    怀
    -0.81
    懷
    -0.76
    logrus
    -0.75
    ازه
    -0.75
     номина
    -0.73
    ină
    -0.72
    ầu
    -0.71
     started
    -0.70
    未使用
    -0.70
     from
    -0.70
    POSITIVE LOGITS
     sold
    2.05
    sold
    1.80
    Sold
    1.50
     copies
    1.47
     sprzed
    1.38
     Sold
    1.34
     vendidos
    1.30
     прода
    1.29
     units
    1.27
     worldwide
    1.26
    Activations Density 0.038%

    No Known Activations