© 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. 84979
    Prev
    Next
    INDEX
    Explanations

    original content programming

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

    This neuron activates on uppercase metadata labels and key terms in document “sidebar” or category blocks—e.g. channel names, “original programming,” network identifiers, and other header‐style tags.

    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
     publicado
    -0.81
     televiz
    -0.75
    ᾥ
    -0.75
    ገ
    -0.75
    発売
    -0.73
     stili
    -0.71
     televisión
    -0.70
    늙
    -0.70
     Retail
    -0.69
     merawat
    -0.69
    POSITIVE LOGITS
     original
    2.39
    Original
    2.09
     Original
    2.06
    original
    1.98
     originals
    1.91
    オリジナル
    1.80
     Originals
    1.79
    ORIGINAL
    1.75
     ORIGINAL
    1.64
    原创
    1.60
    Activations Density 0.038%

    No Known Activations