© 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. 10-GEMMASCOPE-RES-131K
    7. 7194
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands and symbols

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

    The neuron detects pieces of LaTeX markup (tokens beginning with backslashes or related command fragments).

    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
     commerciali
    -1.51
    }
    -1.49
     برگزار
    -1.49
     russa
    -1.44
     antiche
    -1.44
     The
    -1.41
     harian
    -1.41
     itens
    -1.39
     elettron
    -1.38
     adding
    -1.38
    POSITIVE LOGITS
    ⎠
    1.65
     quirk
    1.63
     quirks
    1.61
    re
    1.60
     kümmern
    1.59
     erzählen
    1.55
    ers
    1.55
     enam
    1.52
    в
    1.52
    ighed
    1.52
    Activations Density 0.055%

    No Known Activations