© 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. 34-GEMMASCOPE-RES-131K
    7. 65016
    Prev
    Next
    INDEX
    Explanations

    table related contexts

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

    The neuron flags occurrences of the word “table” (and its use in code or HTML attributes) in technical or code snippets.

    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
     typically
    -0.84
     PHILLIPS
    -0.82
     gali
    -0.75
    äft
    -0.75
    drake
    -0.75
    合理的
    -0.74
    philips
    -0.74
    oarece
    -0.73
     geel
    -0.73
    安全的
    -0.72
    POSITIVE LOGITS
     esophagus
    0.82
     Table
    0.81
     contestant
    0.80
    咕
    0.79
    teen
    0.79
    Table
    0.78
     transplantation
    0.77
     pleine
    0.75
     vš
    0.73
     rRNA
    0.73
    Activations Density 0.028%

    No Known Activations