© 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-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 17001
    Prev
    Next
    INDEX
    Explanations

    washing, washed, washes

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

    wash and rinse

    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_53_width_65k_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
    ajara
    0.39
    鋲
    0.38
     transcribed
    0.37
    দানে
    0.37
     Georgian
    0.37
     दम
    0.36
    ہور
    0.36
    Vlad
    0.35
    Georgian
    0.35
    lineContainer
    0.34
    POSITIVE LOGITS
     wash
    4.03
     washing
    3.95
    洗
    3.94
     washed
    3.89
     washes
    3.78
    washing
    3.48
    Wash
    3.48
    wash
    3.47
     Washing
    3.44
     Wash
    3.42
    Activations Density 0.186%

    No Known Activations