© 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. 10-GEMMASCOPE-RES-131K
    7. 45164
    Prev
    Next
    INDEX
    Explanations

    making a purchase

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

    The neuron fires on occurrences of the word “purchase” (and its inflected forms), i.e. the act of buying something.

    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
    )
    -3.14
    ."
    -2.94
    t
    -2.64
     -
    -2.59
    ge
    -2.48
    is
    -2.34
     was
    -2.28
    /
    -2.27
    СКИ
    -2.23
    后
    -2.22
    POSITIVE LOGITS
    鄠
    2.91
    ↵
    2.86
    谖
    2.83
    轱
    2.70
    沨
    2.66
    愎
    2.66
    閙
    2.52
    了一个
    2.44
    谞
    2.42
     одном
    2.41
    Activations Density 0.007%

    No Known Activations