© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 76284
    Prev
    Next
    INDEX
    Explanations

    building, production, construction

    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
     katalog
    -1.11
    Warna
    -1.00
     ekos
    -0.99
     allemande
    -0.95
    inä
    -0.94
     Katalog
    -0.94
    methode
    -0.94
     tebal
    -0.93
     牛仔
    -0.93
     fotogra
    -0.93
    POSITIVE LOGITS
     production
    1.95
     buildings
    1.52
     workers
    1.41
     building
    1.29
     producing
    1.20
     construction
    1.20
     citizens
    1.20
     produces
    1.20
     produce
    1.20
     productivity
    1.16
    Activations Density 0.018%

    No Known Activations