© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14731
    Prev
    Next
    INDEX
    Explanations

    questions and answers

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

    The neuron fires on the backslash character (“\”), i.e. it detects LaTeX or math‐mode command markers.

    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
     from
    -2.16
     when
    -2.02
     through
    -1.95
     what
    -1.93
     in
    -1.70
    ført
    -1.66
     on
    -1.57
     at
    -1.55
     serves
    -1.55
     reminded
    -1.55
    POSITIVE LOGITS
    <bos>
    1.99
     élar
    1.92
    _
    1.85
    ⚌
    1.69
     rassemb
    1.66
     大きい
    1.63
     they
    1.63
     rafraî
    1.62
     ursprüng
    1.61
     wacky
    1.59
    Activations Density 0.000%

    No Known Activations