© 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. 16507
    Prev
    Next
    INDEX
    Explanations

    SQL table definitions

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

    The neuron is triggered by SQL column constraint keywords, especially “NOT NULL.”

    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
     kateg
    -1.15
     beide
    -0.95
    两个
    -0.95
    菠
    -0.93
     kedua
    -0.92
    zeption
    -0.91
     проекты
    -0.91
    itten
    -0.90
    かれた
    -0.90
     herida
    -0.90
    POSITIVE LOGITS
     jd
    0.93
    OLVE
    0.90
     vw
    0.87
     quran
    0.86
     *:
    0.86
    굴
    0.85
     thorium
    0.84
     seoul
    0.84
     holi
    0.83
     waifu
    0.82
    Activations Density 0.009%

    No Known Activations