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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13006
    Prev
    Next
    INDEX
    Explanations

    parts of words from various languages

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

    The neuron is looking for Latin scientific terms—especially taxonomic abbreviations (like “subsp”) and enzyme names ending in “-nuclease.”

    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
     事例
    -2.45
    uremberg
    -2.38
    er
    -2.38
    忪
    -2.34
     různých
    -2.33
    delion
    -2.27
     参考
    -2.25
     pretože
    -2.25
     každ
    -2.22
    硯
    -2.22
    POSITIVE LOGITS
    a
    3.97
    c
    3.86
    e
    3.48
    鉏
    2.95
    s
    2.94
    am
    2.91
    ا
    2.86
    os
    2.77
     lyd
    2.75
    the
    2.67
    Activations Density 0.489%

    No Known Activations