© 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. 10-GEMMASCOPE-RES-131K
    7. 128
    Prev
    Next
    INDEX
    Explanations

    news stories about people

    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_10/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
    bof
    -1.34
    🎓
    -1.23
     și
    -1.21
     соответственно
    -1.21
    ]],
    -1.21
    bble
    -1.18
     모든
    -1.18
    кая
    -1.18
     ,\
    -1.18
    ithe
    -1.16
    POSITIVE LOGITS
     already
    1.59
     của
    1.59
     doesn
    1.59
     help
    1.57
     monasterio
    1.49
     have
    1.48
     anklicken
    1.41
    ของ
    1.41
     will
    1.38
     กัน
    1.38
    Activations Density 0.290%

    No Known Activations