© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 113691
    Prev
    Next
    INDEX
    Explanations

    parentheses with specific context

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

    This neuron detects spans of Chinese text (Chinese characters and punctuation).

    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
    
    -2.38
     was
    -2.02
    !"
    -2.00
     assists
    -1.95
    鮠
    -1.91
    很少
    -1.80
    のかも
    -1.78
     launchers
    -1.75
    ཽ
    -1.75
     gerente
    -1.71
    POSITIVE LOGITS
    ).
    3.72
    {
    2.91
    </u>
    2.22
    呖
    2.13
     –
    2.09
    a
    1.92
    ,’
    1.91
    >
    1.89
    ),
    1.84
     PyLong
    1.83
    Activations Density 0.008%

    No Known Activations