© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95501
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and symbols

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

    The neuron specializes in spotting LaTeX “\int” integral commands (i.e. occurrences of integrals) in mathematical text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    攢
    -1.28
    orghe
    -1.21
     eenige
    -1.20
    禦
    -1.18
     serdecznie
    -1.16
     bezoekers
    -1.16
     eenvou
    -1.15
     vrienden
    -1.14
     Includes
    -1.13
     aprobación
    -1.13
    POSITIVE LOGITS
     (
    1.16
    ggiare
    1.14
     berle
    1.09
     you
    1.05
     when
    1.05
    ۜ
    1.05
    ！
    1.04
     your
    1.03
     humanas
    1.00
     urbanas
    0.99
    Activations Density 0.005%

    No Known Activations