© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 199006
    Prev
    Next
    INDEX
    Explanations

    water and foreign words

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

    water and watery concepts

    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_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     другим
    0.50
    нтэр
    0.45
    ttä
    0.43
    ів
    0.43
    考える
    0.43
    тивних
    0.42
     примерно
    0.42
    黙
    0.42
    申し
    0.42
    琀
    0.40
    POSITIVE LOGITS
     WATER
    0.54
     水
    0.53
     acqua
    0.52
     gallons
    0.51
     water
    0.51
     wody
    0.51
     ውሃ
    0.50
     Water
    0.48
     waterways
    0.48
     wires
    0.47
    Activations Density 0.001%

    No Known Activations