© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 100651
    Prev
    Next
    INDEX
    Explanations

    database configuration settings

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

    references to database connection pools, data sources, and connection-related classes or configurations in code.

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

    The neuron activates on programming identifiers and configuration terms for data‐source setup (e.g. “DataSource,” “Configuration,” “Factory,” connection “url,” etc.).

    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
    بحث
    -1.49
    椟
    -1.48
    ésie
    -1.47
    ina
    -1.44
     când
    -1.38
     its
    -1.38
    似乎
    -1.33
    菝
    -1.32
    》,
    -1.30
     PERSPECT
    -1.30
    POSITIVE LOGITS
     after
    1.46
    </strong>
    1.45
    0
    1.39
    .
    1.34
     revolución
    1.34
    <bos>
    1.34
    睃
    1.34
     Egyes
    1.29
    してみました
    1.28
    巅峰
    1.27
    Activations Density 0.012%

    No Known Activations