© 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. 4284
    Prev
    Next
    INDEX
    Explanations

    construction contracts awarded

    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
    FACTORY
    -0.85
    izde
    -0.78
    Factory
    -0.75
     AIRCRAFT
    -0.74
    Hearing
    -0.73
    Interaction
    -0.72
    Практи
    -0.71
    ♔
    -0.69
    Warehouse
    -0.69
     Viitattu
    -0.69
    POSITIVE LOGITS
     construction
    1.95
     contractor
    1.72
     contractors
    1.66
     Construction
    1.57
    construction
    1.48
     constructor
    1.41
     engineering
    1.28
    Contractor
    1.28
     Contractor
    1.27
     constructors
    1.27
    Activations Density 0.026%

    No Known Activations