© 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. 44085
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with numbers

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

    The neuron fires on floating‐point numeric literals (decimal numbers) within technical or mathematical 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
     deudas
    -1.55
    armani
    -1.43
    ünkü
    -1.34
     romántica
    -1.33
    ⇹
    -1.32
     imediatamente
    -1.29
     creciendo
    -1.27
     rebajas
    -1.25
    IconModule
    -1.24
    marzo
    -1.24
    POSITIVE LOGITS
     camere
    1.50
     a
    1.42
    :
    1.37
     **/
    1.36
     we
    1.34
    asinya
    1.34
     raso
    1.24
     fono
    1.24
     Enciclopedia
    1.22
     canta
    1.21
    Activations Density 0.283%

    No Known Activations