© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108768
    Prev
    Next
    INDEX
    Explanations

    SQL Server, Oracle, scripts

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

    The neuron fires on tokens naming Oracle database APIs, drivers, namespaces, and error codes (e.g. “oci,” “oracle::,” “cx_Oracle,” “ORA-…,” “PLS-…”).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    abetta
    -0.84
    zzata
    -0.81
    Packs
    -0.79
     tableName
    -0.78
     Weldon
    -0.77
     tulis
    -0.77
    შ
    -0.76
     Darío
    -0.73
     knit
    -0.72
    heights
    -0.71
    POSITIVE LOGITS
    Ʉ
    0.79
     TextInputType
    0.73
    ArrayOf
    0.72
     Facebook
    0.72
     Pinto
    0.71
     Ya
    0.71
     сбор
    0.69
    ☦
    0.68
    𝗣
    0.68
     село
    0.66
    Activations Density 0.008%

    No Known Activations