© 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. 108439
    Prev
    Next
    INDEX
    Explanations

    pre-, q:, short-

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

    This neuron detects occurrences of the CSS “!important” declaration (the “!” plus “important”).

    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
    ！
    -0.88
    ％
    -0.87
    !
    -0.86
    calloc
    -0.85
     createState
    -0.84
    xlarge
    -0.82
    ！(
    -0.82
    éenne
    -0.79
     excelente
    -0.79
     TextAppearance
    -0.79
    POSITIVE LOGITS
     wichtiger
    1.16
     Более
    0.91
     wichtigen
    0.84
     zuvor
    0.83
    important
    0.83
     gebaut
    0.81
     dreary
    0.81
    ものに
    0.80
    inee
    0.78
    minente
    0.77
    Activations Density 0.004%

    No Known Activations