© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 117244
    Prev
    Next
    INDEX
    Explanations

    banner ads

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

    The neuron activates on advertisement‐related terms and formatting tokens (e.g. “banner,” “ad,” “graphic,” “formats,” “click”).

    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
    CHD
    -0.84
    찍
    -0.77
    arap
    -0.75
     critica
    -0.73
    jMenu
    -0.72
    кладки
    -0.71
     asisten
    -0.70
     preparo
    -0.69
    참고
    -0.69
     Osm
    -0.68
    POSITIVE LOGITS
     banner
    2.16
     banners
    2.08
    banner
    1.70
    Banner
    1.60
    banners
    1.55
     Banner
    1.53
     Banners
    1.36
     image
    1.31
     ads
    1.16
     images
    1.13
    Activations Density 0.051%

    No Known Activations