© 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. 7031
    Prev
    Next
    INDEX
    Explanations

    nautical terms

    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
     tourism
    -0.95
     cruises
    -0.84
     hotel
    -0.79
     tourists
    -0.79
    iliki
    -0.75
     hotels
    -0.75
     Motel
    -0.75
     Tourism
    -0.74
    旅游
    -0.74
     Feminist
    -0.73
    POSITIVE LOGITS
     onboard
    1.31
     deck
    1.05
     aft
    1.04
    aft
    1.01
    deck
    0.99
     Deck
    0.96
    Deck
    0.86
     forward
    0.85
     DECK
    0.82
    艙
    0.82
    Activations Density 0.006%

    No Known Activations