© 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
    2. Gemma-3-12B
    3. 24-GEMMASCOPE-2-RES-16K
    4. 4625
    Prev
    Next
    INDEX
    Explanations

    process-related nouns/verbs

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

    The neuron strongly fires on phrases that state product or service availability, quantities, and delivery/offering details (e.g. “only 1 left in stock,” “pick up and delivery available,” “express delivery available”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     какого
    0.73
     spôsob
    0.71
     театра
    0.70
     تعالیٰ
    0.69
     каком
    0.68
     რომელი
    0.67
    躡
    0.67
     생각을
    0.66
     그것
    0.66
    ਾਵ
    0.66
    POSITIVE LOGITS
    绝对
    0.71
    ES
    0.68
     Nearby
    0.67
    ED
    0.66
    :
    0.66
     entrant
    0.65
     per
    0.64
    nearby
    0.64
    ර්ධ
    0.63
    →
    0.63
    Activations Density 0.110%

    No Known Activations