© 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. 10-GEMMASCOPE-RES-131K
    7. 65428
    Prev
    Next
    INDEX
    Explanations

    matrix and function

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

    This neuron activates on occurrences of “matrix” (i.e., references to matrices or matrix‐related notation).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    wasn
    -1.84
    didn
    -1.71
    看起来
    -1.66
    couldn
    -1.66
    started
    -1.64
    wouldn
    -1.63
    葙
    -1.59
    established
    -1.59
    isn
    -1.59
    Understand
    -1.55
    POSITIVE LOGITS
     for
    2.70
     by
    1.88
     if
    1.80
     that
    1.76
    \
    1.73
    鏷
    1.65
    笕
    1.52
     allowing
    1.51
     Canadá
    1.44
     vendedor
    1.44
    Activations Density 0.069%

    No Known Activations