© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93077
    Prev
    Next
    INDEX
    Explanations

    database table column names

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

    The neuron strongly activates on SQL data‐definition and schema-related tokens (e.g. CREATE TABLE, PRIMARY KEY, column names) in code snippets.

    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
    ラーメン
    -0.80
    东京
    -0.77
     chấp
    -0.76
    صورة
    -0.76
    フジテレビ
    -0.73
    inction
    -0.73
    遵守
    -0.73
     Achieving
    -0.73
     env
    -0.72
     вашей
    -0.72
    POSITIVE LOGITS
    DataContract
    1.10
     COLUMN
    1.03
    COLUMN
    1.03
     table
    0.88
     Reality
    0.85
     vnd
    0.84
    Contract
    0.82
     contracts
    0.82
     contract
    0.79
    reality
    0.78
    Activations Density 0.010%

    No Known Activations