© 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-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 9473
    Prev
    Next
    INDEX
    Explanations

    marine ocean

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

    ocean temperature and currents

    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_40_width_16k_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
    土壤
    0.61
    土地
    0.60
    Soil
    0.57
     जमीन
    0.56
     почвы
    0.55
    锹
    0.55
    陇
    0.55
    Chhattisgarh
    0.54
     땅
    0.54
    垡
    0.54
    POSITIVE LOGITS
     ocean
    1.70
     oceanic
    1.57
     seabed
    1.55
     marine
    1.52
    海洋
    1.50
     seaf
    1.48
     Ocean
    1.43
    ocean
    1.42
     оке
    1.41
    Ocean
    1.41
    Activations Density 0.233%

    No Known Activations