© 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. 66004
    Prev
    Next
    INDEX
    Explanations

    cleanliness

    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
     to
    -0.90
     явно
    -0.89
     alcuni
    -0.84
    lanted
    -0.80
     ofrecen
    -0.80
     lenient
    -0.78
     einzelne
    -0.75
    せよ
    -0.75
     leaky
    -0.73
     sufren
    -0.73
    POSITIVE LOGITS
     clean
    2.31
     tidy
    1.88
    clean
    1.84
    Clean
    1.62
     Clean
    1.54
     CLEAN
    1.52
    tidy
    1.48
     sạch
    1.45
     bersih
    1.40
    CLEAN
    1.38
    Activations Density 0.017%

    No Known Activations