© 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. 111001
    Prev
    Next
    INDEX
    Explanations

    auctions and financial offers

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

    The neuron activates on auction‐ and bidding‐related terms (e.g. “bid,” “bidding,” “bidder,” “auction”).

    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
     of
    -3.14
    
    -2.95
    镚
    -2.94
    媄
    -2.83
    𐄁
    -2.64
     Eleven
    -2.61
     ४
    -2.55
    出了一
    -2.38
     $
    -2.36
    vantaged
    -2.36
    POSITIVE LOGITS
    [
    3.05
    '
    2.72
    鄚
    2.63
    </strong>
    2.61
    廛
    2.58
    #
    2.47
    *
    2.44
     improbable
    2.42
    {
    2.39
    漚
    2.33
    Activations Density 0.005%

    No Known Activations