© 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. 42801
    Prev
    Next
    INDEX
    Explanations

    latex document elements

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

    This neuron fires on LaTeX footnote content (the text inside \footnote{…} commands).

    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
    "
    -1.88
     "
    -1.55
    那個
    -1.50
    之为
    -1.48
     said
    -1.46
    那種
    -1.45
     affirme
    -1.43
     continúas
    -1.41
    <bos>
    -1.41
     prouve
    -1.40
    POSITIVE LOGITS
    lgari
    1.73
    多久
    1.72
    itattu
    1.70
     However
    1.61
    variates
    1.59
     dévou
    1.59
     bohemian
    1.58
     ۱۱
    1.58
     namun
    1.58
    """
    1.58
    Activations Density 0.006%

    No Known Activations