© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 59510
    Prev
    Next
    INDEX
    Explanations

    television networks news sports

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

    The neuron activates on references to media outlets, particularly broadcast news network names and their abbreviations.

    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
    POUR
    -0.84
     lã
    -0.84
     ilha
    -0.81
    футболка
    -0.79
     guitarra
    -0.79
     cueva
    -0.77
     foco
    -0.77
    ને
    -0.76
     walker
    -0.76
     lengua
    -0.76
    POSITIVE LOGITS
     News
    2.41
     news
    1.90
    News
    1.86
    news
    1.73
     Sports
    1.63
    NEWS
    1.41
     NEWS
    1.34
    新闻
    1.23
    ニュース
    1.20
    sports
    1.17
    Activations Density 0.026%

    No Known Activations