© 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. 117822
    Prev
    Next
    INDEX
    Explanations

    large data volumes and processing

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

    The neuron responds to mentions of “data” and related technical terms—especially in contexts of analytics, processing, and big-data discussion.

    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
    dropIfExists
    -0.90
    Lista
    -0.88
    ähig
    -0.87
    گوشی
    -0.86
    UniqueId
    -0.84
     pantalla
    -0.81
    tabl
    -0.81
     unsha
    -0.79
    jän
    -0.79
    lá
    -0.79
    POSITIVE LOGITS
     data
    1.61
     voluminous
    1.55
     vast
    1.51
     massive
    1.47
    ormous
    1.45
     حجم
    1.41
     immense
    1.41
    massive
    1.39
     volume
    1.37
     huge
    1.36
    Activations Density 0.138%

    No Known Activations