© 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. 65938
    Prev
    Next
    INDEX
    Explanations

    NPR, religieuses, Identität

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

    This neuron detects the byline and attribution lines in news articles (the source name, reporter’s name, and location metadata).

    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
     viewer
    -0.88
     Freezer
    -0.81
     viewers
    -0.79
     grafik
    -0.75
     futbol
    -0.75
     armées
    -0.74
     Fête
    -0.74
    潜在
    -0.73
     vald
    -0.73
     kino
    -0.72
    POSITIVE LOGITS
     NPR
    1.11
    NPR
    1.02
     religieux
    1.00
     PHPUnit
    0.88
     religieuse
    0.86
     recording
    0.85
     insieme
    0.84
    taka
    0.83
     што
    0.82
     Identität
    0.81
    Activations Density 0.003%

    No Known Activations