© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 93393
    Prev
    Next
    INDEX
    Explanations

    route description, selection, or change

    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
    罴
    -1.09
     році
    -1.00
    ',
    -0.98
     люди
    -0.97
    lossians
    -0.94
    为什么
    -0.94
    Eight
    -0.92
    昨日
    -0.91
    höhe
    -0.90
     ancients
    -0.90
    POSITIVE LOGITS
     Route
    1.34
     çekilen
    1.18
     route
    1.14
    ить
    1.13
     маршру
    1.13
     Routes
    1.11
     nacionais
    1.09
    Route
    1.09
     ROUTE
    1.04
    ROUTE
    1.03
    Activations Density 0.016%

    No Known Activations