© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 71805
    Prev
    Next
    INDEX
    Explanations

    \begin{latex} command

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

    This neuron detects occurrences of the keyword “begin” (e.g. the LaTeX `\begin{…}` command) that mark the start of an environment.

    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
     a
    -2.13
    c
    -2.06
     the
    -2.03
    ate
    -1.94
    u
    -1.85
    b
    -1.84
    了不少
    -1.82
    ong
    -1.77
     ‘
    -1.73
    了许多
    -1.71
    POSITIVE LOGITS
    jadikan
    1.59
     and
    1.59
    🕗
    1.56
     that
    1.55
    illoin
    1.52
    gamot
    1.51
     will
    1.50
    ombang
    1.49
     این
    1.47
    razione
    1.46
    Activations Density 0.005%

    No Known Activations