© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 57538
    Prev
    Next
    INDEX
    Explanations

    Co-

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

    The neuron is triggered almost exclusively by the LaTeX display‐math opening delimiter “\[,” i.e. the start of a displayed math block.

    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
     içi
    -0.84
    Hauptartikel
    -0.80
    󠁷
    -0.76
    쌓
    -0.76
     सकती
    -0.75
    Postup
    -0.75
     köpek
    -0.75
     olarak
    -0.75
    Flas
    -0.75
    Seguro
    -0.73
    POSITIVE LOGITS
    begin
    0.91
     who
    0.87
     начинается
    0.83
    began
    0.82
     начать
    0.81
     starts
    0.79
     begins
    0.77
    攀
    0.77
     Begin
    0.77
    ره
    0.76
    Activations Density 0.000%

    No Known Activations