© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 61576
    Prev
    Next
    INDEX
    Explanations

    wash dishes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     запись
    0.46
    纤维
    0.44
     просмотра
    0.42
    鲔
    0.42
    icks
    0.42
    ucha
    0.41
    ケー
    0.41
    или
    0.41
     न्यायमूर्ति
    0.41
    velt
    0.40
    POSITIVE LOGITS
     washing
    1.21
     Washing
    1.12
     wash
    1.04
    washing
    1.00
     washed
    1.00
     washes
    0.95
     洗
    0.92
    洗
    0.89
     rửa
    0.86
     Wash
    0.86
    Activations Density 0.038%

    No Known Activations