© 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. 34-GEMMASCOPE-RES-131K
    7. 29933
    Prev
    Next
    INDEX
    Explanations

    links with http or www

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

    Explanation of neuron 4 behavior: the main thing this neuron does is find web URLs or domain name references.

    oai_token-act-pair · o4-mini
    Triggered 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
    Negative Logits
     but
    -1.13
     what
    -1.07
     czerwca
    -0.92
    !!!
    -0.92
    </i>
    -0.91
     (
    -0.90
    !!
    -0.87
     Three
    -0.87
    V
    -0.86
     Due
    -0.85
    POSITIVE LOGITS
    Bericht
    1.22
    
    1.17
    😙
    1.13
    Suche
    1.10
    wwww
    1.10
    libatkan
    1.05
    獁
    1.05
     実例
    1.04
    Komentar
    1.02
     広場
    1.02
    Activations Density 0.009%

    No Known Activations