© 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. 48051
    Prev
    Next
    INDEX
    Explanations

    quotation marks and brackets

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

    This neuron detects East Asian-style quotation marks and title brackets (e.g. “ ” and 《》).

    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
    \
    -2.59
    ar
    -2.44
    </h3>
    -2.22
    </h1>
    -2.16
    the
    -2.08
    </strong>
    -1.90
    <em>
    -1.89
    骉
    -1.89
    </blockquote>
    -1.88
    妧
    -1.88
    POSITIVE LOGITS
    ',
    3.22
     Kecil
    2.44
    ᾐ
    2.38
     này
    2.25
     About
    1.97
    ’
    1.97
    ،
    1.95
    
    1.94
    CCIÓN
    1.93
    ,"
    1.92
    Activations Density 0.002%

    No Known Activations