© 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. 19577
    Prev
    Next
    INDEX
    Explanations

    incentive pay and design

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

    This neuron primarily activates on occurrences of the word “incentive” (and its plurals/variants) in the text.

    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
    廕
    -2.98
     we
    -2.97
    写真を
    -2.72
    of
    -2.58
     Geschä
    -2.39
     accomplishments
    -2.33
     that
    -2.31
    ons
    -2.28
    抺
    -2.28
     tredje
    -2.25
    POSITIVE LOGITS
    ⬮
    2.47
    のほうが
    2.47
     добавля
    2.28
    酹
    2.27
    that
    2.25
    了他的
    2.25
    だわ
    2.23
     แท้
    2.20
    でしたが
    2.20
     ruth
    2.16
    Activations Density 0.002%

    No Known Activations