© 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. 31-GEMMASCOPE-2-RES-262K
    7. 2960
    Prev
    Next
    INDEX
    Explanations

    water

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

    water and hydration levels

    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
    Not in Any Lists

    No Comments

    Negative Logits
     गैंगस्टर
    0.53
    詆
    0.50
     აღმასრულებელი
    0.50
    掸
    0.48
    导演
    0.48
     वर्दी
    0.48
    气氛
    0.46
    გუფი
    0.46
    बंधन
    0.46
    ხედ
    0.46
    POSITIVE LOGITS
     water
    1.97
     Water
    1.67
     agua
    1.64
    water
    1.63
     água
    1.58
     WATER
    1.58
    水
    1.55
    Water
    1.50
    水的
    1.48
    水の
    1.43
    Activations Density 0.182%

    No Known Activations