© 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. 10-GEMMASCOPE-RES-131K
    7. 111381
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and symbols

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

    The neuron detects numeric constants (especially decimals) and arithmetic operators within math‐style expressions.

    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
    There
    -2.30
    Some
    -1.84
     there
    -1.79
    What
    -1.66
    Something
    -1.65
    One
    -1.63
    After
    -1.62
    .
    -1.52
    но
    -1.48
    _
    -1.45
    POSITIVE LOGITS
     to
    2.06
     in
    1.82
    mpagne
    1.81
     a
    1.81
    leggings
    1.76
    chrys
    1.67
    versace
    1.66
    aning
    1.65
    jesus
    1.64
    buddha
    1.63
    Activations Density 0.396%

    No Known Activations