© 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. 37716
    Prev
    Next
    INDEX
    Explanations

    creator, star, maker, singer

    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
    才是
    -0.89
     vejo
    -0.75
     Managerial
    -0.75
    itmen
    -0.74
    тій
    -0.73
    ISODE
    -0.71
    というもの
    -0.71
     vermittelt
    -0.70
     itch
    -0.69
     Оста
    -0.68
    POSITIVE LOGITS
     maker
    1.06
     and
    1.02
     provider
    0.96
     creator
    0.93
    Framework
    0.82
     composer
    0.80
     groupe
    0.79
     seller
    0.78
    PROVIDER
    0.77
    maker
    0.76
    Activations Density 0.029%

    No Known Activations