© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12668
    Prev
    Next
    INDEX
    Explanations

    closing parenthesis or numbers

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

    The neuron activates on the specific token sequence of a closing double‐quote immediately followed by a right parenthesis (`")`), as when ending a string literal in code.

    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
     versão
    -1.84
     múl
    -1.83
    僰
    -1.80
    {~
    -1.73
     perpé
    -1.72
    苤
    -1.66
    𝟑
    -1.63
     statt
    -1.63
     neuer
    -1.57
     estud
    -1.56
    POSITIVE LOGITS
     that
    2.50
     which
    2.05
     or
    1.91
    这般
    1.77
     barnet
    1.67
     wezen
    1.64
     is
    1.63
     johnny
    1.63
     bijvoorbeeld
    1.61
     if
    1.55
    Activations Density 0.000%

    No Known Activations