© 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. 10-GEMMASCOPE-RES-131K
    7. 12581
    Prev
    Next
    INDEX
    Explanations

    latex document structure

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

    The neuron fires on LaTeX environment openings, i.e. the “\begin{…}” command and its environment name.

    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
    g
    -1.98
    n
    -1.97
    b
    -1.94
    t
    -1.91
    ne
    -1.90
    r
    -1.89
    0
    -1.88
    5
    -1.80
    na
    -1.69
    d
    -1.66
    POSITIVE LOGITS
     from
    2.23
     by
    1.79
    ();*/
    1.65
    {
    1.59
     if
    1.58
     like
    1.51
    اعده
    1.51
     at
    1.48
    zji
    1.47
     between
    1.44
    Activations Density 0.003%

    No Known Activations