© 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. 99896
    Prev
    Next
    INDEX
    Explanations

    WordPress site paths

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

    The neuron selectively fires on the parts of HTML attributes that contain URL paths (especially in link/href attributes pointing to stylesheets).

    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
     pasado
    -0.76
     enviable
    -0.76
     ayude
    -0.75
     vanden
    -0.74
    小姐
    -0.74
    悟
    -0.73
    maxLines
    -0.72
    ząd
    -0.71
     Ticket
    -0.71
    ᠬ
    -0.70
    POSITIVE LOGITS
     home
    1.43
    stylesheet
    1.08
     blog
    1.03
    url
    0.92
    home
    0.90
     blogs
    0.90
     domov
    0.88
    Home
    0.87
     homeostasis
    0.83
     network
    0.81
    Activations Density 0.019%

    No Known Activations