© 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. 130140
    Prev
    Next
    INDEX
    Explanations

    The neuron strongly activates on code snippets—especially SQL statements and keywords (like “INSERT … SELECT …”) embedded in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    custom code entries

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     Jeu
    -1.01
    ског
    -0.94
     汉
    -0.90
     técn
    -0.89
     TÜ
    -0.88
    мать
    -0.88
    🔑
    -0.88
     Fjord
    -0.86
     Parigi
    -0.86
    Виды
    -0.85
    POSITIVE LOGITS
    同じく
    1.05
     natomiast
    1.00
     similarly
    0.93
     аналоги
    0.92
     ebenso
    0.86
     Второй
    0.86
    second
    0.86
     Глав
    0.84
    SECOND
    0.84
     Second
    0.82
    Activations Density 0.100%

    No Known Activations