© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 32833
    Prev
    Next
    INDEX
    Explanations

    quoted words or phrases

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

    The neuron strongly activates on words or phrases enclosed in quotation marks.

    oai_token-act-pair · o4-mini
    Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     nuclé
    -1.09
    椁
    -1.01
    他們
    -1.01
    Ұ
    -1.00
    yoga
    -1.00
     hôtels
    -0.99
     Ree
    -0.99
     TEACHER
    -0.99
     whatnot
    -0.99
     lutar
    -0.98
    POSITIVE LOGITS
     sites
    1.18
     -
    1.13
     Other
    1.12
    ,"
    1.12
    之地
    0.98
    を入
    0.97
    .'"
    0.97
    '.
    0.97
    )-
    0.96
     or
    0.96
    Activations Density 0.038%

    No Known Activations