© 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. 90479
    Prev
    Next
    INDEX
    Explanations

    html meta content

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

    This neuron fires on HTML `<meta>` tags—especially the `http-equiv` directives (e.g. the “X-UA-Compatible” meta tag) in the document head.

    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
     Tacos
    -0.79
    ؐ
    -0.77
    Tit
    -0.76
    MV
    -0.75
     आधार
    -0.74
    edan
    -0.72
     tacos
    -0.71
     orgasm
    -0.69
     explo
    -0.68
    LATEST
    -0.68
    POSITIVE LOGITS
     gestos
    0.74
    ostructures
    0.71
    anthus
    0.69
    Norfolk
    0.68
    elerik
    0.67
     темно
    0.66
     Lagrange
    0.65
    soli
    0.65
    ApiRequest
    0.65
    ற
    0.65
    Activations Density 0.051%

    No Known Activations