© 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. 2744
    Prev
    Next
    INDEX
    Explanations

    shipbuilding and shipyards

    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
     airport
    -0.76
     Cone
    -0.76
     distributor
    -0.75
     aeropuerto
    -0.74
     cone
    -0.74
    дзі
    -0.74
     terdengar
    -0.73
     Frankfurt
    -0.73
     распростра
    -0.72
     Mickey
    -0.72
    POSITIVE LOGITS
     shipbuilding
    1.88
     shipyard
    1.85
    建造
    1.56
     yard
    1.34
     yards
    1.27
     build
    1.22
     builders
    1.21
    yard
    1.20
     builder
    1.17
    builder
    1.12
    Activations Density 0.046%

    No Known Activations