© 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. 10-GEMMASCOPE-RES-131K
    7. 12542
    Prev
    Next
    INDEX
    Explanations

    items listed as buildings or companies

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

    The neuron activates on instances of “listed” or “listing” (and related phrasing) indicating that something is formally listed—e.g. on a stock exchange, a property register, or a heritage list.

    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
     Atención
    -2.50
    <bos>
    -1.89
    隐隐
    -1.86
    ⚢
    -1.78
     livrer
    -1.73
    袛
    -1.67
    ℣
    -1.65
    殮
    -1.64
     バック
    -1.63
    tiskt
    -1.63
    POSITIVE LOGITS
     on
    1.95
     für
    1.83
     at
    1.81
     &
    1.80
     an
    1.72
    哔
    1.72
    listed
    1.71
    /*++
    1.67
     fenómeno
    1.65
     sarana
    1.65
    Activations Density 0.011%

    No Known Activations