© 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. 7854
    Prev
    Next
    INDEX
    Explanations

    advertising banners

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

    The neuron fires for mentions of banners or banner displays—especially in contexts like championship banners or other prominent hanging signs.

    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
    הו
    -0.80
     Acceler
    -0.77
    Ще
    -0.76
     accelerate
    -0.72
    JOURNAL
    -0.72
    看出
    -0.71
    lägen
    -0.71
    patrol
    -0.71
    acceler
    -0.71
     accelerating
    -0.71
    POSITIVE LOGITS
     banner
    4.88
     banners
    4.03
     Banner
    3.98
    banner
    3.84
    Banner
    3.64
    banners
    2.84
     Banners
    2.78
     BAN
    1.94
    BAN
    1.74
     бан
    1.38
    Activations Density 0.028%

    No Known Activations