© 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. 22-GEMMASCOPE-RES-131K
    7. 70438
    Prev
    Next
    INDEX
    Explanations

    free shipping

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

    The neuron detects marketing‐style promotional offers—especially mentions of coupons, free shipping, discounts, and similar deal language.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     other
    -1.47
     three
    -1.46
     nine
    -1.41
     five
    -1.41
     eight
    -1.39
     two
    -1.36
     four
    -1.33
     it
    -1.20
     his
    -1.19
     fuß
    -1.19
    POSITIVE LOGITS
     your
    1.52
     you
    1.41
     kilometer
    1.27
    閾
    1.27
    йся
    1.24
     implor
    1.24
    COMMENT
    1.23
     soportes
    1.17
     ouver
    1.16
     nouveautés
    1.15
    Activations Density 0.010%

    No Known Activations