© 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. 111905
    Prev
    Next
    INDEX
    Explanations

    subsets and mathematical set operations

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

    This neuron detects LaTeX command or escape tokens (the backslash character in math notation).

    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
     “
    -2.23
    0
    -2.20
    ,”
    -2.11
    e
    -2.11
    !”
    -2.06
    I
    -1.88
    うーん
    -1.86
    
    -1.84
     “.
    -1.83
    N
    -1.83
    POSITIVE LOGITS
     mußte
    2.38
     '
    2.33
    unikasi
    2.09
     alojamientos
    1.98
     museos
    1.93
     müßte
    1.88
     Países
    1.87
     pertenecen
    1.87
     wußte
    1.84
     schwed
    1.82
    Activations Density 0.025%

    No Known Activations