© 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. 84705
    Prev
    Next
    INDEX
    Explanations

    advertising and marketing platforms

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

    The neuron fires strongly on advertising terms—especially tokens like “Ad,” “Words,” “Ads,” etc.—i.e. mentions of ad services such as AdWords/AdMob/AdSense.

    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
    atelle
    -0.81
     ~=
    -0.79
     chuyền
    -0.78
     german
    -0.75
    itting
    -0.73
    inge
    -0.72
    hade
    -0.71
    issima
    -0.71
    讨论
    -0.69
    iced
    -0.69
    POSITIVE LOGITS
     Ads
    1.09
    Ads
    1.07
     advertising
    0.98
     advertiser
    0.94
     advertisers
    0.91
     Advertising
    0.88
     Ad
    0.81
    Auction
    0.78
    Advertising
    0.77
     Advertiser
    0.77
    Activations Density 0.006%

    No Known Activations