© 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. 37963
    Prev
    Next
    INDEX
    Explanations

    construction and building industries

    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
    計画
    -0.69
     collector
    -0.67
     installations
    -0.65
     geschützt
    -0.64
     Rasen
    -0.64
     collectors
    -0.64
     operator
    -0.64
     Collectors
    -0.63
     prototype
    -0.63
     Tees
    -0.63
    POSITIVE LOGITS
     construction
    2.20
     Construction
    1.94
    Construction
    1.88
     building
    1.81
    construction
    1.66
    Building
    1.57
     construcción
    1.54
    CONSTRUCTION
    1.51
     Building
    1.50
    建筑
    1.49
    Activations Density 0.027%

    No Known Activations