© 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. 10-GEMMASCOPE-RES-131K
    7. 103703
    Prev
    Next
    INDEX
    Explanations

    matrix structure

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

    The neuron fires on LaTeX matrix environments (i.e. occurrences of the token “matrix”).

    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
    𓋼
    -2.02
    出來的
    -1.98
    還會
    -1.92
     oes
    -1.90
    醞
    -1.82
     erwähnten
    -1.81
    ↵↵
    -1.77
     wilden
    -1.77
    紧接着
    -1.75
    也會
    -1.72
    POSITIVE LOGITS
     are
    2.30
     has
    2.28
     we
    2.08
     from
    2.05
     when
    2.02
     on
    1.89
    osgi
    1.88
     in
    1.79
     as
    1.73
     these
    1.73
    Activations Density 0.001%

    No Known Activations