© 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. 7292
    Prev
    Next
    INDEX
    Explanations

    smuggling and busts

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

    The neuron activates on numeric expressions indicating quantities (especially weights, measures, and 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_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
     gradually
    -0.82
     for
    -0.78
     all
    -0.78
     spend
    -0.77
     faudra
    -0.75
     causing
    -0.75
     drinking
    -0.73
     getting
    -0.73
     borrowed
    -0.73
     understand
    -0.73
    POSITIVE LOGITS
     smuggling
    1.77
     smugglers
    1.38
     smuggled
    1.36
     smug
    1.35
     busts
    1.10
     cargo
    1.06
     ukry
    1.06
    attempt
    1.05
     shipment
    1.02
    Attempt
    1.02
    Activations Density 0.017%

    No Known Activations