© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 127703
    Prev
    Next
    INDEX
    Explanations

    This neuron detects URL components (e.g., “https”, “://”, and related link markup).

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408

    links to URLs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     ausgewählt
    -1.05
     voicing
    -0.95
    depuis
    -0.95
    ров
    -0.93
    thers
    -0.91
    门
    -0.91
     ſeveral
    -0.90
     começou
    -0.90
     tornou
    -0.89
     subsequent
    -0.88
    POSITIVE LOGITS
     or
    1.22
     your
    1.05
     sienten
    0.94
     pursuant
    0.89
    accéder
    0.88
     ebenfalls
    0.87
    TestBed
    0.86
     fièvre
    0.86
    おきます
    0.86
    予定です
    0.86
    Activations Density 0.001%

    No Known Activations