© 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. 34-GEMMASCOPE-RES-131K
    7. 65687
    Prev
    Next
    INDEX
    Explanations

    HTML class and completion

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

    The neuron fires on attribute or keyword identifiers in code or markup (e.g. HTML tag attributes like class/style, DOCTYPE keywords like PUBLIC, and code annotation names).

    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
    synchronize
    -0.86
    NDR
    -0.81
    Tienes
    -0.81
     |]
    -0.80
     принять
    -0.79
    сных
    -0.77
    țin
    -0.77
     duplo
    -0.77
    Preguntas
    -0.76
    iks
    -0.76
    POSITIVE LOGITS
     Duck
    0.79
    Yard
    0.76
     журнали
    0.76
     duck
    0.75
    Duck
    0.75
    鸽
    0.75
     Dish
    0.74
    )=
    0.74
     Kashmir
    0.73
     стене
    0.71
    Activations Density 0.000%

    No Known Activations