© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 65451
    Prev
    Next
    INDEX
    Explanations

    mathematical notation for matrices and functions

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

    The neuron is detecting LaTeX matrix environment tokens (e.g. “\begin{matrix}”, “pmatrix”, “bmatrix”).

    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
     欣赏
    -1.58
    дают
    -1.48
     estrenar
    -1.46
     but
    -1.45
    各种
    -1.38
    cją
    -1.36
     menghapus
    -1.34
     Since
    -1.34
    しますが
    -1.33
     mencari
    -1.30
    POSITIVE LOGITS
     \
    1.94
    al
    1.71
    ar
    1.55
     marvelous
    1.55
    螃
    1.48
     voisins
    1.45
     coworkers
    1.45
    I
    1.43
     DURING
    1.42
    fgaben
    1.41
    Activations Density 0.001%

    No Known Activations