© 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. 113055
    Prev
    Next
    INDEX
    Explanations

    mathematical variables and symbols

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

    The main thing this neuron does is pick out individual math‐formula symbols (single‐letter variables and parameters) inside LaTeX or inline equations.

    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
     this
    -2.05
     that
    -1.56
     and
    -1.43
     for
    -1.30
     new
    -1.29
     become
    -1.28
     everything
    -1.21
    のご紹介
    -1.20
     with
    -1.18
     primeiras
    -1.18
    POSITIVE LOGITS
     incluidos
    1.33
    antism
    1.31
     mentre
    1.30
    给他们
    1.30
     quando
    1.30
    tuce
    1.29
    !***
    1.26
    riors
    1.26
    atische
    1.24
    </h2>
    1.22
    Activations Density 0.046%

    No Known Activations