© 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. 22-GEMMASCOPE-RES-131K
    7. 25987
    Prev
    Next
    INDEX
    Explanations

    vendors, sellers, and street performers

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

    The neuron is detecting mentions of vendors or sellers (especially in street‐food or informal market contexts).

    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
     alip
    -1.10
     atap
    -1.05
     wanda
    -1.03
     vincere
    -1.02
     corporate
    -1.02
    hounds
    -1.02
    みます
    -1.02
    毆
    -1.02
    ŚĆ
    -1.00
    ichiro
    -1.00
    POSITIVE LOGITS
     selling
    1.67
    Selling
    1.24
     sells
    1.22
     sellers
    1.20
     витами
    1.19
     ингреди
    1.18
     vendors
    1.17
    selling
    1.16
    ขาย
    1.16
     lös
    1.12
    Activations Density 0.046%

    No Known Activations