© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 32578
    Prev
    Next
    INDEX
    Explanations

    bathtub cleaning

    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
     imping
    0.40
    疙
    0.40
     मेहंदी
    0.38
     Rocket
    0.37
    cooled
    0.37
     reckoned
    0.37
    ingle
    0.35
     Exchange
    0.35
     Ki
    0.35
     rushed
    0.35
    POSITIVE LOGITS
     bathtub
    1.69
    bathtub
    1.44
     tub
    1.41
     tubs
    1.38
     bath
    1.30
     baths
    1.26
    浴
    1.17
    Bath
    1.14
    bath
    1.13
    Tub
    1.10
    Activations Density 0.003%

    No Known Activations