© 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. 86755
    Prev
    Next
    INDEX
    Explanations

    making or receiving offers

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

    The neuron fires on numerical tokens—any standalone numbers, years, prices, or similar digit sequences.

    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
     semblent
    -0.86
    鹳
    -0.77
    APOLIS
    -0.75
    opener
    -0.73
    toler
    -0.73
    iformis
    -0.72
    CTG
    -0.71
    veur
    -0.71
    iduous
    -0.71
    IENCE
    -0.71
    POSITIVE LOGITS
     offer
    7.31
     offers
    6.28
     offered
    6.19
     Offer
    6.03
    Offer
    5.97
    offer
    5.84
     OFFER
    5.53
     offering
    5.19
     Offers
    5.13
    Offers
    4.94
    Activations Density 0.137%

    No Known Activations