© 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. 41751
    Prev
    Next
    INDEX
    Explanations

    to do so

    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
    寕
    -2.45
     dedicado
    -2.00
    了一个
    -1.99
     где
    -1.96
     dekoratif
    -1.95
     kenaikan
    -1.90
    勠
    -1.89
    会被
    -1.88
     και
    -1.87
     getrock
    -1.83
    POSITIVE LOGITS
     They
    2.20
    躥
    1.97
     ‘
    1.86
     In
    1.85
    ни
    1.81
     “
    1.74
    se
    1.72
    ти
    1.72
     However
    1.66
    ”
    1.66
    Activations Density 0.019%

    No Known Activations