© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 65088
    Prev
    Next
    INDEX
    Explanations

    enron.com or Rod

    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
     to
    -1.87
     of
    -1.27
     bæ
    -1.13
     harus
    -1.13
     klasse
    -1.08
     Italie
    -1.06
     karena
    -1.05
     nacht
    -1.05
    zoll
    -1.04
    готовки
    -1.03
    POSITIVE LOGITS
     rijden
    1.30
     exclusivamente
    1.14
     beschik
    1.13
     uzyskać
    1.09
    クエ
    1.08
    lösen
    1.07
    سكري
    1.07
    っており
    1.05
     adecuadamente
    1.05
     môžete
    1.05
    Activations Density 0.232%

    No Known Activations