© 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. 107757
    Prev
    Next
    INDEX
    Explanations

    field and code definitions

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

    This neuron fires on CamelCase framework class and field names in code snippets, particularly Django/DRF serializers and model form field types.

    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
    Тарихы
    -0.78
     budú
    -0.78
     Genomics
    -0.76
    fontFamily
    -0.75
     Monty
    -0.74
    oida
    -0.74
    βά
    -0.73
    ząc
    -0.72
    zib
    -0.71
     Geschwindigkeit
    -0.71
    POSITIVE LOGITS
    widget
    1.05
     help
    1.02
     required
    0.91
     widget
    0.91
     Required
    0.90
    label
    0.86
     label
    0.86
     Tula
    0.85
    required
    0.83
    Widget
    0.82
    Activations Density 0.004%

    No Known Activations