© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 13172
    Prev
    Next
    INDEX
    Explanations

    wash: cleaning or trading

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     स्वीकृत
    0.40
    靘
    0.39
     aprobado
    0.39
    弈
    0.38
    耱
    0.38
    ığı
    0.38
     обеспечение
    0.38
    کومت
    0.38
    AddModelError
    0.37
     APPROVED
    0.37
    POSITIVE LOGITS
     wash
    1.03
     washing
    1.02
     Washing
    1.01
     洗
    0.92
     Wash
    0.91
     washes
    0.91
     lavado
    0.91
    Wash
    0.91
     washed
    0.90
    washing
    0.89
    Activations Density 0.005%

    No Known Activations