© 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. 83894
    Prev
    Next
    INDEX
    Explanations

    news and media outlets

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

    This neuron activates on the names of media outlets, websites, or other publication brands.

    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
    參考文獻
    -0.95
     mistrust
    -0.91
    が
    -0.84
    ⼼
    -0.84
     barrio
    -0.84
     morph
    -0.82
     torno
    -0.82
     Aver
    -0.81
    ovec
    -0.81
     Profess
    -0.79
    POSITIVE LOGITS
     News
    1.12
    news
    1.06
     píše
    1.05
    News
    1.03
     Magazine
    1.00
     Новости
    0.98
     görüntüsü
    0.96
    onews
    0.96
    times
    0.94
     Today
    0.93
    Activations Density 0.187%

    No Known Activations