© 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. 32867
    Prev
    Next
    INDEX
    Explanations

    SQL table definition keywords

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

    This neuron flags database schema–migration and table-definition code, such as migration methods (`def change`/`def up`) and SQL/DDL statements (`CREATE TABLE`, column definitions).

    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
     Acesso
    -0.99
    特意
    -0.97
    様に
    -0.95
     Água
    -0.95
     llegó
    -0.94
     みた
    -0.94
     Início
    -0.93
    当局
    -0.92
     different
    -0.89
     Informações
    -0.89
    POSITIVE LOGITS
     of
    1.16
    delser
    1.08
    THAN
    1.06
     gospodar
    1.05
     waschen
    1.03
    <0xA3>
    1.02
    ษ
    1.02
     estadounidense
    1.02
     colegio
    1.00
    ánicas
    0.98
    Activations Density 0.001%

    No Known Activations