© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 3754
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

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

    The neuron fires on LaTeX math‐mode font commands (e.g. “\mathbb”, “\mathcal”) used to denote special sets or styled symbols.

    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
    行きたい
    -1.74
    some
    -1.31
     домов
    -1.25
    6
    -1.25
    2
    -1.25
     some
    -1.23
     привести
    -1.16
    	
    -1.16
     голос
    -1.16
     preguntó
    -1.14
    POSITIVE LOGITS
     then
    1.76
     різних
    1.73
     però
    1.60
     wtedy
    1.54
     разные
    1.50
     Obtenez
    1.48
     тях
    1.47
    гій
    1.46
    στο
    1.45
     бъдат
    1.42
    Activations Density 0.016%

    No Known Activations