© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 4958
    Prev
    Next
    INDEX
    Explanations

    cleaning and washing actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_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
    𝙡
    1.70
    ுக
    1.68
    करार
    1.63
     крае
    1.62
    ルス
    1.61
    śni
    1.57
     roost
    1.57
    边缘
    1.57
     diminution
    1.57
    閂
    1.57
    POSITIVE LOGITS
    滌
    2.13
    涤
    1.94
     detergent
    1.78
    濯
    1.69
    Lett
    1.66
    textAppearance
    1.62
    洗
    1.61
     deterg
    1.60
     धोने
    1.58
     washable
    1.57
    Activations Density 0.474%

    No Known Activations