© 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. 60976
    Prev
    Next
    INDEX
    Explanations

    cleaning or cleaner

    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
    चर्स
    0.38
    ቁ
    0.38
     сокра
    0.37
    ด์
    0.37
     फे
    0.36
    heem
    0.36
     Афри
    0.36
    퉁
    0.36
    obis
    0.35
    ducers
    0.35
    POSITIVE LOGITS
     cleaning
    1.79
     Cleaning
    1.76
    Cleaning
    1.73
     cleaned
    1.61
    cleaning
    1.59
    cleaned
    1.38
    清洗
    1.36
     nettoyage
    1.33
     limpieza
    1.30
     cleaners
    1.28
    Activations Density 0.003%

    No Known Activations