© 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. 92961
    Prev
    Next
    INDEX
    Explanations

    Sony Bravia

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

    The main thing this neuron does is detect LaTeX/math-mode tokens (backslashes, math symbols, and environment keywords).

    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
     then
    -1.45
     this
    -1.33
     would
    -1.18
     apabila
    -1.11
     tersebut
    -1.03
     Introducción
    -1.03
     mümkün
    -0.99
    ⤒
    -0.98
    leine
    -0.98
     that
    -0.97
    POSITIVE LOGITS
     pfalz
    1.21
     gioia
    1.18
     البعض
    1.16
     снова
    1.14
    𝐳
    1.07
    ⏟
    1.07
    IconModule
    1.07
    SetFont
    1.06
     forse
    1.05
    GIVEREF
    1.05
    Activations Density 0.010%

    No Known Activations