© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-16K
    7. 14974
    Prev
    Next
    INDEX
    Explanations

    weather and meteorology

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

    weather data and meteorological conditions

    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_31_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
     akibat
    0.45
    ตัน
    0.45
    iriman
    0.45
    泳
    0.44
    ريع
    0.43
    endorong
    0.43
     لوبه
    0.43
    プール
    0.43
    倭
    0.43
    綰
    0.43
    POSITIVE LOGITS
     meteorological
    1.52
     Weather
    1.43
     Meteorology
    1.43
     meteor
    1.42
     Meteorological
    1.41
     weather
    1.39
    Weather
    1.31
    Meteor
    1.25
     Meteor
    1.23
    weather
    1.17
    Activations Density 0.208%

    No Known Activations