© 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. 10-GEMMASCOPE-RES-131K
    4. 65721
    Prev
    Next
    INDEX
    Explanations

    same file, window, row, line

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

    This neuron detects occurrences of the word “same.”

    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
     in
    -1.94
     see
    -1.81
     need
    -1.73
    ,"
    -1.73
    ';
    -1.63
     would
    -1.60
    }{
    -1.54
     to
    -1.52
     he
    -1.52
     will
    -1.52
    POSITIVE LOGITS
    鱻
    2.05
    不断的
    1.71
     荣耀
    1.70
    ௅
    1.68
    焢
    1.66
    釤
    1.63
    釔
    1.61
     optique
    1.59
     preciosas
    1.57
     producent
    1.55
    Activations Density 0.024%

    No Known Activations