© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 781
    Prev
    Next
    INDEX
    Explanations

    the 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_16k_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
    🥜
    0.73
    莢
    0.73
    棘
    0.69
     Hausdorff
    0.69
     HOMO
    0.68
    🌰
    0.67
    AntiForgery
    0.66
    Decode
    0.66
    BtnPanel
    0.65
    arski
    0.65
    POSITIVE LOGITS
     water
    4.65
     Water
    4.17
    Water
    4.12
    water
    4.00
     WATER
    3.71
     agua
    3.66
     waters
    3.57
    水
    3.57
     água
    3.50
    WATER
    3.46
    Activations Density 1.113%

    No Known Activations