© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 103117
    Prev
    Next
    INDEX
    Explanations

    en-us URLs

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

    The neuron strongly activates on fragments of Microsoft MSDN documentation URLs (e.g., “microsoft.com/en-us/library/…aspx”).

    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
     languages
    -1.12
    日本語
    -1.09
     مؤرشف
    -0.97
     english
    -0.94
     Inglés
    -0.93
     Languages
    -0.90
     bilingual
    -0.90
     English
    -0.89
    中文
    -0.87
    jshint
    -0.86
    POSITIVE LOGITS
    бі
    0.80
    pn
    0.79
     of
    0.75
    endipity
    0.75
     akibat
    0.74
    🐛
    0.73
    to
    0.73
     $('<
    0.73
    骼
    0.73
    bate
    0.72
    Activations Density 0.025%

    No Known Activations