© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 13016
    Prev
    Next
    INDEX
    Explanations

    Call followed by Me

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

    The neuron activates on LaTeX package or library import commands (e.g. “\usepackage…” and “\usetikzlibrary…”).

    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
    -
    -1.90
     to
    -1.77
    _
    -1.59
     ajouter
    -1.56
    栝
    -1.55
    齶
    -1.55
    mination
    -1.53
    凄い
    -1.50
     is
    -1.49
     renowned
    -1.47
    POSITIVE LOGITS
     not
    1.94
     Like
    1.70
     mesmas
    1.66
    底部
    1.54
     see
    1.52
     penumpang
    1.47
    灃
    1.44
     There
    1.43
    That
    1.43
     Although
    1.41
    Activations Density 0.001%

    No Known Activations