© 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. 117029
    Prev
    Next
    INDEX
    Explanations

    latex commands, scientific terms

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

    LaTeX math and technical documentation.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron selectively activates on LaTeX package‐loading commands (the “\usepackage{…}” lines).

    oai_token-act-pair · o4-miniTriggered 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
    jezd
    -0.94
    quark
    -0.88
    FILTER
    -0.87
     webu
    -0.84
     CreateTagHelper
    -0.84
    ANCING
    -0.84
     adverbs
    -0.81
    OCCURRED
    -0.79
    &=\
    -0.79
    )}{\
    -0.78
    POSITIVE LOGITS
    its
    0.90
    venirs
    0.78
     wieder
    0.77
    ずつ
    0.77
     о
    0.77
    here
    0.74
     таких
    0.74
     porcentaje
    0.73
    кор
    0.72
     подготовка
    0.72
    Activations Density 0.000%

    No Known Activations