© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 60091
    Prev
    Next
    INDEX
    Explanations

    streaming web content

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

    This neuron specializes in detecting named entities and other proper nouns—such as people’s names, organization names, and titles.

    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
     sentra
    -0.97
     ayudarte
    -0.87
     Moreover
    -0.85
     movie
    -0.81
     hof
    -0.81
     MOVIE
    -0.78
    Unspecified
    -0.76
    carpus
    -0.76
    heritance
    -0.75
    婭
    -0.75
    POSITIVE LOGITS
     web
    1.18
    web
    1.15
    Web
    1.04
     streaming
    0.99
    Creator
    0.98
     Netflix
    0.96
    Amazon
    0.95
     Amazon
    0.94
     Web
    0.92
    Netflix
    0.91
    Activations Density 0.009%

    No Known Activations