© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 72839
    Prev
    Next
    INDEX
    Explanations

    descriptions for companies and organizations

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

    The neuron primarily detects mentions of company or organization names (especially with formal corporate identifiers).

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    geox
    -1.72
    banyak
    -1.70
     naše
    -1.66
    sergio
    -1.66
    libros
    -1.61
    noticia
    -1.60
     orejas
    -1.58
     cejas
    -1.56
     joyería
    -1.55
     bluz
    -1.54
    POSITIVE LOGITS
    swire
    1.84
    byes
    1.63
    xed
    1.62
    њу
    1.55
    kind
    1.54
    try
    1.50
    nological
    1.49
    кратно
    1.46
    fra
    1.45
    抑郁
    1.45
    Activations Density 0.155%

    No Known Activations