© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 99002
    Prev
    Next
    INDEX
    Explanations

    paste HTML in website

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

    This neuron detects instructions for embedding or linking content—phrases like “Embed this on your website,” “Copy this code,” or “paste this HTML” that tell you how to share or embed an object.

    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
    omla
    -0.81
    ARGB
    -0.79
    ագրություն
    -0.74
    ucca
    -0.72
    SAB
    -0.72
    cased
    -0.71
    Decoder
    -0.68
    versing
    -0.68
    optional
    -0.68
    gency
    -0.68
    POSITIVE LOGITS
    Charged
    0.77
     healthful
    0.72
    水面
    0.69
    Walls
    0.68
    niques
    0.68
    metodo
    0.68
     UIApplication
    0.67
    Faq
    0.66
    ESSIONS
    0.66
     guer
    0.66
    Activations Density 0.076%

    No Known Activations