© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 6100
    Prev
    Next
    INDEX
    Explanations

    US state abbreviations

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

    The neuron detects U.S. state abbreviations (the two-letter postal codes) in addresses.

    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
    ждую
    0.62
    ①
    0.60
    orphan
    0.57
    рах
    0.54
    řed
    0.54
    requireNonNull
    0.54
     चिह्नित
    0.54
     thuyết
    0.54
    ementerian
    0.54
    aciju
    0.53
    POSITIVE LOGITS
     Capri
    0.60
     Retail
    0.60
     shopper
    0.59
     HSBC
    0.59
     Afgh
    0.59
     Burberry
    0.58
    ?
    0.58
     Wm
    0.57
     jpg
    0.57
     meal
    0.57
    Activations Density 0.013%

    No Known Activations