© 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. 37745
    Prev
    Next
    INDEX
    Explanations

    context and following words

    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
     punter
    -0.86
    Народ
    -0.82
    cuentos
    -0.79
    Ǯ
    -0.78
     apes
    -0.77
    redients
    -0.75
    ኬ
    -0.75
    lottery
    -0.75
    Lottery
    -0.74
    Муж
    -0.73
    POSITIVE LOGITS
    ual
    1.38
    menu
    1.36
     menu
    1.23
    ually
    1.20
    Menu
    0.97
     Menu
    0.90
    UAL
    0.86
    анд
    0.85
     menus
    0.84
     заказать
    0.83
    Activations Density 0.019%

    No Known Activations