© 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. 41671
    Prev
    Next
    INDEX
    Explanations

    for all

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

    The neuron is specialized to pick up LaTeX math‐mode formatting tokens—things like alignment markers (&, \\), commands such as “\text,” and the surrounding braces.

    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
     a
    -1.57
    注明
    -1.45
    
    -1.38
     später
    -1.38
     údaje
    -1.37
    マニア
    -1.32
    𒊹
    -1.30
    ครื่อง
    -1.29
    Organisator
    -1.28
     venido
    -1.27
    POSITIVE LOGITS
     both
    1.58
     all
    1.50
    </em>
    1.41
    2
    1.41
    termilk
    1.40
    ternut
    1.38
     they
    1.35
     those
    1.34
     these
    1.31
     each
    1.31
    Activations Density 0.019%

    No Known Activations