© 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. 10-GEMMASCOPE-RES-131K
    7. 6709
    Prev
    Next
    INDEX
    Explanations

    database indexes

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

    The main thing this neuron does is detect mentions of SQL indexing operations (e.g. “INDEX”, “clustered”, “on”, “unique”, etc.).

    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_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ჻
    -1.55
    躥
    -1.52
    ㍑
    -1.50
    
    -1.42
    もあった
    -1.41
    dő
    -1.41
     assister
    -1.40
     juiste
    -1.40
     様子
    -1.37
    ྥ
    -1.37
    POSITIVE LOGITS
     on
    2.14
     at
    2.02
     not
    1.91
    </h4>
    1.61
    s
    1.54
     for
    1.50
    者に
    1.39
     гг
    1.38
     לה
    1.37
    a
    1.35
    Activations Density 0.016%

    No Known Activations