© 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. 83334
    Prev
    Next
    INDEX
    Explanations

    bidding

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

    This neuron detects numeric tokens—especially dollar amounts, bids, and other auction‐related numbers.

    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
    голь
    -0.79
    abonnement
    -0.78
    SEASON
    -0.77
    Buff
    -0.75
     doInBackground
    -0.75
    leur
    -0.74
     testen
    -0.73
     Sele
    -0.73
    markets
    -0.73
    belt
    -0.71
    POSITIVE LOGITS
     bidding
    4.13
     bid
    3.94
     bids
    3.66
     bidders
    3.30
     bidder
    3.22
    bid
    3.19
    Bid
    3.09
     Bid
    2.89
     Bidding
    2.86
    Bidding
    2.78
    Activations Density 0.037%

    No Known Activations