© 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. 34-GEMMASCOPE-RES-131K
    7. 83121
    Prev
    Next
    INDEX
    Explanations

    price tag

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

    The neuron activates on mentions of “price” (especially the phrase “price tag” with adjectives like “hefty” or “big”), i.e. occurrences of pricing information.

    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
    eref
    -0.87
    ກ
    -0.77
     Pict
    -0.76
    QUOTE
    -0.75
     Rates
    -0.75
    titled
    -0.75
    人気の
    -0.75
    Kat
    -0.74
    Тут
    -0.74
     Meilleures
    -0.74
    POSITIVE LOGITS
     price
    4.72
    price
    3.16
     Price
    2.84
    Price
    2.83
     PRICE
    2.53
    PRICE
    2.50
     precio
    2.08
     tag
    2.00
     цена
    1.91
     preço
    1.87
    Activations Density 0.032%

    No Known Activations