© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 2350
    Prev
    Next
    INDEX
    Explanations

    of water

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    TDto
    0.72
    novae
    0.68
     egin
    0.64
    णारी
    0.64
     emoticon
    0.64
    蛏
    0.61
     saree
    0.61
    чив
    0.60
    getAsDouble
    0.60
    żeń
    0.60
    POSITIVE LOGITS
     water
    5.40
    water
    4.72
    Water
    4.70
     Water
    4.70
     WATER
    4.23
    水
    4.14
     agua
    4.06
     воды
    4.00
     água
    3.99
    WATER
    3.95
    Activations Density 0.430%

    No Known Activations