© 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. 128182
    Prev
    Next
    INDEX
    Explanations

    numbers in mathematical expressions

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

    The neuron specializes in spotting numeric tokens (numbers, whether integers or decimals, including those in formulas or code).

    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
    
    -1.43
    欺负
    -1.37
    >
    -1.34
     increasingly
    -1.34
    罴
    -1.24
    看一下
    -1.23
    肮
    -1.23
     conqu
    -1.23
    宦
    -1.20
     our
    -1.20
    POSITIVE LOGITS
     in
    1.77
     or
    1.56
     to
    1.36
    These
    1.32
     estekak
    1.29
     at
    1.25
     termasuk
    1.25
     آن‌ها
    1.23
     —
    1.23
     sekitarnya
    1.23
    Activations Density 0.076%

    No Known Activations