© 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. 40106
    Prev
    Next
    INDEX
    Explanations

    wash, rinse, hydrate

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

    aids in washing or hydrating

    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
    盯着
    0.42
    阳光
    0.41
    截
    0.39
    太阳
    0.38
    ूती
    0.38
     gelap
    0.38
    屽
    0.38
    ད་
    0.37
     ඉ
    0.37
    爸爸
    0.36
    POSITIVE LOGITS
     rinsing
    0.67
     wash
    0.64
     rửa
    0.63
     flushing
    0.62
     洗
    0.61
     hydrate
    0.61
     धोने
    0.61
    洗
    0.61
     rinse
    0.60
     flushed
    0.60
    Activations Density 0.109%

    No Known Activations