© 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. 22-GEMMASCOPE-RES-131K
    4. 93384
    Prev
    Next
    INDEX
    Explanations

    database command preparation and execution

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

    The neuron responds to database‐API method names (e.g. prepareStatement, createStatement, executeQuery, SqlCommand), i.e. calls involved in preparing or executing SQL queries.

    oai_token-act-pair · o4-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    嗑
    -1.20
     quando
    -1.15
    翆
    -1.13
    thodoxy
    -1.05
     první
    -1.02
     The
    -1.01
    thodox
    -1.00
     มา
    -0.99
     acht
    -0.97
    :
    -0.96
    POSITIVE LOGITS
     紋
    1.38
    
    1.34
    بسم
    1.27
    糴
    1.24
    دانلود
    1.22
    <0xF3>
    1.21
    ngoing
    1.21
    Татьяна
    1.20
     Cfr
    1.16
    Ирина
    1.16
    Activations Density 0.001%

    No Known Activations