© 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. 34-GEMMASCOPE-RES-131K
    7. 53965
    Prev
    Next
    INDEX
    Explanations

    start of document or diagram

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

    This neuron detects TeX environment boundary commands, especially the “\begin{document}” and “\end{document}” tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     relative
    -0.86
     esperado
    -0.76
     welcomed
    -0.72
     Jahrh
    -0.72
    www
    -0.71
     होता
    -0.71
    لى
    -0.71
     order
    -0.71
     r
    -0.71
     approximate
    -0.70
    POSITIVE LOGITS
     inond
    0.93
    schuhe
    0.88
     ekor
    0.86
    Jeden
    0.84
    {@
    0.83
    Jetzt
    0.83
     intrig
    0.82
     Muñoz
    0.82
    Fuß
    0.82
    ఈ
    0.82
    Activations Density 0.001%

    No Known Activations