© 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. 105860
    Prev
    Next
    INDEX
    Explanations

    quotation marks

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

    This neuron detects quotation-mark characters (opening or closing single or double quotes).

    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
    巨大的
    -2.58
     
    -2.05
     any
    -1.98
    ৄ
    -1.88
     customised
    -1.83
     pengurus
    -1.77
    에는
    -1.76
     ​
    -1.75
     llegó
    -1.74
     feito
    -1.70
    POSITIVE LOGITS
     be
    2.42
     februari
    2.25
     and
    2.25
     radeon
    2.03
    屨
    1.99
    क्स
    1.97
    桖
    1.95
     augustus
    1.91
    
    1.91
     手机
    1.90
    Activations Density 0.031%

    No Known Activations