© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 89990
    Prev
    Next
    INDEX
    Explanations

    dependent database definitions

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

    The neuron detects programming‐language configuration or schema directives—tokens like DEFAULT, ENGINE, AUTO_INCREMENT, equals signs, colons, and similar keywords used in code for setting defaults or defining table properties.

    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
     microfibra
    -0.77
     사이
    -0.76
    nitř
    -0.75
     took
    -0.75
     Escola
    -0.73
     denso
    -0.73
    countable
    -0.72
     still
    -0.72
     challenging
    -0.72
     almost
    -0.71
    POSITIVE LOGITS
    imid
    1.05
    umbe
    0.90
    FORCE
    0.90
     FORCE
    0.88
     cascade
    0.87
    )}^{
    0.85
    cascade
    0.84
     charset
    0.82
    ccas
    0.80
    argli
    0.79
    Activations Density 0.003%

    No Known Activations