© 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. 65708
    Prev
    Next
    INDEX
    Explanations

    parenthetical abbreviations

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

    The neuron strongly activates on parentheses and the tokens that mark parenthetical segments (e.g. “(…)", “)”), i.e. it finds parenthetical expressions.

    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
    乆
    -2.19
     they
    -2.13
    敺
    -2.03
    觏
    -2.03
    後面
    -1.93
     brindar
    -1.91
    
    -1.88
    硖
    -1.85
    يته
    -1.82
    ꦒ
    -1.81
    POSITIVE LOGITS
    翃
    2.28
     \
    2.19
    蓠
    2.03
     impec
    1.95
    an
    1.88
    rozco
    1.84
    方的
    1.83
     illustre
    1.82
    ranton
    1.81
    also
    1.77
    Activations Density 0.219%

    No Known Activations