© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 111061
    Prev
    Next
    INDEX
    Explanations

    latex commands

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

    LaTeX command backslashes in technical or code documents.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5

    The neuron primarily detects LaTeX command introducers, i.e. the backslash tokens that start TeX commands.

    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
    '
    -2.84
    ll
    -2.47
    leurs
    -2.31
    也
    -2.30
     untuk
    -2.30
     voor
    -2.28
     برای
    -2.22
    荧
    -2.13
     Luar
    -2.13
     Then
    -2.11
    POSITIVE LOGITS
    不由得
    2.89
    踮
    2.45
     become
    2.44
     \
    2.33
    </b>
    2.33
    ᚔ
    2.31
    \
    2.23
     seeming
    2.23
    鼙
    2.23
    >
    2.16
    Activations Density 0.005%

    No Known Activations