© 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. 129903
    Prev
    Next
    INDEX
    Explanations

    dinitrobenzene or dinitrophenyl

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

    Chinese characters and related text in technical or scientific documents.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron activates on Chinese (Han) characters.

    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
    '
    -2.66
     hundred
    -2.63
    ers
    -2.58
     erns
    -2.56
     crucial
    -2.50
     صفحۀ
    -2.48
    k
    -2.48
    獼
    -2.34
     ferocious
    -2.34
    ya
    -2.33
    POSITIVE LOGITS
    ᪥
    3.00
    arraycopy
    2.92
     ткани
    2.86
    0
    2.86
     When
    2.81
    鱻
    2.81
    おめでとうございます
    2.77
     plethora
    2.69
    ｵ
    2.64
    お疲れ様でした
    2.59
    Activations Density 0.001%

    No Known Activations