© 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. 98591
    Prev
    Next
    INDEX
    Explanations

    TV, entertainment, and specific writers

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    pekt
    -0.72
    Monument
    -0.71
    Pulitzer
    -0.68
    nahmen
    -0.66
    stories
    -0.65
     служба
    -0.65
    Alfa
    -0.65
     Pulitzer
    -0.65
    )$-
    -0.65
     dipping
    -0.65
    POSITIVE LOGITS
     entertainment
    1.65
     Entertainment
    1.50
    Entertainment
    1.40
    Variety
    1.32
     Variety
    1.27
    entertainment
    1.26
     entretenimiento
    1.13
     Television
    1.11
    娛樂
    1.08
     TV
    1.03
    Activations Density 0.094%

    No Known Activations