© 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. 129341
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and equations

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

    The neuron flags numeric literals in the text—especially standalone numbers and decimal constants.

    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
    <blockquote>
    -2.00
     Categor
    -1.86
    <h2>
    -1.84
    ꜆
    -1.84
    s
    -1.71
    \
    -1.66
    <h3>
    -1.59
     では
    -1.58
    ౮
    -1.54
    bena
    -1.53
    POSITIVE LOGITS
    ࿙
    1.88
    ımda
    1.72
    饧
    1.70
    ৄ
    1.67
    Fakta
    1.64
    Aplicaciones
    1.63
     conferencias
    1.63
    Imágenes
    1.63
    seleccion
    1.63
    พวก
    1.62
    Activations Density 0.017%

    No Known Activations