© 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. 64503
    Prev
    Next
    INDEX
    Explanations

    news, articles, stories, video

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

    This neuron detects the presence of URLs (web links) by activating strongly on domain names, slashes, and path segments.

    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_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     for
    -1.81
     to
    -1.30
     of
    -1.28
    CollectionUtils
    -1.15
     like
    -1.15
     poitrine
    -1.09
    евна
    -1.02
     Arquivado
    -1.01
     tabi
    -0.98
     hogyan
    -0.95
    POSITIVE LOGITS
    があるので
    1.42
     męska
    1.38
     news
    1.34
     carregar
    1.32
     SHOWS
    1.30
    Pendidikan
    1.29
     nová
    1.28
    guarantee
    1.27
     respiración
    1.27
     story
    1.25
    Activations Density 0.021%

    No Known Activations