© 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. 93978
    Prev
    Next
    INDEX
    Explanations

    HTML link rel attribute

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

    The neuron is keyed to HTML `<link rel="stylesheet">` elements.

    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
     anmelden
    -0.76
     vun
    -0.74
    责任编辑
    -0.74
    方向
    -0.71
    갯
    -0.68
    hány
    -0.68
    vrons
    -0.68
    鄴
    -0.67
    Frontier
    -0.67
    IsContent
    -0.65
    POSITIVE LOGITS
    exels
    0.78
     integran
    0.69
     aplican
    0.68
     Twelve
    0.68
    jordan
    0.68
    casts
    0.66
    userService
    0.64
     chileno
    0.63
     χρή
    0.63
     werken
    0.63
    Activations Density 0.034%

    No Known Activations