© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 34839
    Prev
    Next
    INDEX
    Explanations

    cleaning items and actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Calm
    -0.78
    sság
    -0.77
     такъ
    -0.75
    གས་
    -0.75
     دریافت‌شده
    -0.73
    utuhan
    -0.73
     watered
    -0.71
     đóng
    -0.70
     abiertas
    -0.70
     remplacé
    -0.70
    POSITIVE LOGITS
     cleaning
    4.38
     clean
    3.77
     cleaned
    3.72
    cleaning
    3.36
     Cleaning
    3.22
     cleanliness
    3.16
     cleans
    3.06
    Cleaning
    3.05
    clean
    3.03
    CLEAN
    3.00
    Activations Density 0.041%

    No Known Activations