© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 58139
    Prev
    Next
    INDEX
    Explanations

    "Rango decimales" and "CATCH"

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

    The neuron is primarily detecting HTML/XML markup tags (e.g. “<i>”).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     soyez
    -1.76
     живут
    -1.72
    Encyclopædia
    -1.68
    ό
    -1.68
    専用の
    -1.57
    ॐ
    -1.56
     tarifi
    -1.52
    агностика
    -1.50
     savez
    -1.48
     anadolu
    -1.45
    POSITIVE LOGITS
    genicity
    1.35
     iż
    1.30
     were
    1.29
    ervative
    1.27
     Of
    1.27
    Т
    1.27
    讨论
    1.27
    ícias
    1.26
    頂いた
    1.24
    .);
    1.23
    Activations Density 0.001%

    No Known Activations