© 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-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 6967
    Prev
    Next
    INDEX
    Explanations

    ship sailing nautical seafaring maritime

    np_acts-logits-general · gemini-2.5-flash-lite

    ships, sailing, maritime

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pestic
    0.47
    쫀득
    0.45
     রাস্তার
    0.45
     तेंद
    0.44
     কীট
    0.43
     Pestic
    0.43
    💆
    0.43
     दलित
    0.42
     निजामा
    0.42
     झर
    0.42
    POSITIVE LOGITS
    船
    3.14
     ship
    3.06
     sailing
    2.97
     ships
    2.88
     кораб
    2.83
     sailors
    2.78
     জাহাজ
    2.78
    船舶
    2.78
     nautical
    2.67
     sail
    2.66
    Activations Density 0.365%

    No Known Activations