© 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. 22-GEMMASCOPE-RES-131K
    7. 27300
    Prev
    Next
    INDEX
    Explanations

    code statements or commands

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

    The neuron is strongly triggered by SQL “INSERT INTO” phrases, i.e. tokens belonging to an INSERT INTO statement.

    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
     інших
    -0.98
    tapete
    -0.95
    cías
    -0.94
    全て
    -0.94
    pD
    -0.93
     AspNetCore
    -0.92
     ▸
    -0.91
     розвитку
    -0.90
    much
    -0.89
     pescoço
    -0.89
    POSITIVE LOGITS
     etc
    1.53
     ....
    1.34
     ..
    1.27
    ....
    1.23
    ...
    1.18
     ...
    1.17
    xx
    1.16
    ○○
    1.12
    xxx
    1.09
     xxx
    1.08
    Activations Density 0.264%

    No Known Activations