© 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. 34-GEMMASCOPE-RES-131K
    7. 1160
    Prev
    Next
    INDEX
    Explanations

    latex matrix and array environments

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

    This neuron detects LaTeX environment‐opening constructs (e.g. “\begin{cases},” “array,” “pmatrix,” etc.) in mathematical expressions.

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

    LaTeX mathematical environments and matrices, particularly the `\begin{cases}`, `\begin{array}`, `\begin{bmatrix}`, `\begin{pmatrix}`, and `\begin{matrix}` commands.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    LaTeX math-environment structure markers indicating piecewise definitions, matrices, and aligned arrays (including alignment and line-break syntax).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    }{@
    -0.84
    ionic
    -0.80
    channelId
    -0.79
    ]);
    -0.77
     Variante
    -0.77
     yet
    -0.76
     منها
    -0.75
    ])]
    -0.75
    Salmo
    -0.75
    )];
    -0.74
    POSITIVE LOGITS
    although
    0.93
    Гля
    0.84
     BOTH
    0.82
     although
    0.80
     something
    0.75
    SSON
    0.75
    같이
    0.75
     अच्छी
    0.73
     Mays
    0.73
    preneurs
    0.71
    Activations Density 0.006%

    No Known Activations