© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 99778
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols

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

    The neuron is detecting LaTeX inline‐math delimiters (the “$” tokens that begin and end math mode).

    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
    -
    -3.00
    .
    -2.84
    But
    -2.67
    In
    -2.66
    And
    -2.63
    er
    -2.53
    Such
    -2.52
    Let
    -2.50
    Basically
    -2.48
    かなり
    -2.47
    POSITIVE LOGITS
     in
    2.80
    cigarettes
    2.48
    }$.
    2.47
    罡
    2.45
     they
    2.34
    錚
    2.33
    alisco
    2.33
     at
    2.31
     alebo
    2.28
     or
    2.27
    Activations Density 0.050%

    No Known Activations