© 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. 48154
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure

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

    The neuron strongly fires on closing curly braces “}” in LaTeX code.

    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
    LOADER
    -0.82
    𝘪
    -0.79
    niosek
    -0.77
     judicia
    -0.77
     অ
    -0.76
    ปลา
    -0.75
    ﹋
    -0.75
     коли
    -0.75
    buch
    -0.73
    ന്ന
    -0.73
    POSITIVE LOGITS
     она
    0.85
     Defines
    0.81
    šan
    0.81
    Nyt
    0.77
    祜
    0.76
    0.75
     \%
    0.75
     Lade
    0.75
     Ust
    0.74
     varones
    0.74
    Activations Density 0.005%

    No Known Activations