© 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. 41-GEMMASCOPE-2-RES-262K
    7. 33774
    Prev
    Next
    INDEX
    Explanations

    wet wipes

    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_all/layer_41_width_262k_l0_big
    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
    sous
    0.44
     Sutherland
    0.43
    Krishna
    0.41
    പാ
    0.40
    GOND
    0.40
    穵
    0.38
    鍋
    0.38
    잔
    0.37
    軽量
    0.37
    Sous
    0.37
    POSITIVE LOGITS
     wipes
    1.82
     wipe
    1.52
     Wipe
    1.41
    wipe
    1.36
     wiped
    1.30
     wiping
    1.20
     wet
    0.99
    Wet
    0.93
     Wet
    0.91
    湿
    0.91
    Activations Density 0.005%

    No Known Activations