© 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. 11582
    Prev
    Next
    INDEX
    Explanations

    database and db concepts

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

    the word "database" or its translations in various languages (base de datos, база данных, Datenbank, etc.).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    This neuron detects mentions of “database” (including variants like “Datenbank,” “база данных,” or “base” in “SQL base”).

    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
    </h2>
    -2.56
    </h5>
    -1.80
    </td>
    -1.78
    </em>
    -1.77
    鹮
    -1.73
     That
    -1.72
    外界
    -1.63
     quedaba
    -1.63
     weiße
    -1.59
     bluntly
    -1.56
    POSITIVE LOGITS
    姈
    1.89
    in
    1.85
     DATABASE
    1.77
     RESTAURANT
    1.62
     databases
    1.58
     DICTION
    1.55
     שלהם
    1.52
     it
    1.51
    見つ
    1.51
    人の
    1.49
    Activations Density 0.054%

    No Known Activations