© 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. 129169
    Prev
    Next
    INDEX
    Explanations

    The neuron detects backslash characters marking the start of LaTeX (or similar markup) commands.

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

    start of descriptive phrases

    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
     ของ
    -1.05
    LoadScene
    -1.02
    INER
    -0.98
     pasas
    -0.97
     exista
    -0.95
     Vorgang
    -0.94
     interesan
    -0.94
     sés
    -0.93
    SIZES
    -0.93
    chec
    -0.92
    POSITIVE LOGITS
    .
    0.97
     and
    0.92
    ⓒ
    0.90
    After
    0.87
     noastre
    0.86
    There
    0.85
    felizmente
    0.85
    幾乎
    0.83
    ះ
    0.82
    That
    0.82
    Activations Density 0.000%

    No Known Activations