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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 69935
    Prev
    Next
    INDEX
    Explanations

    de before nouns

    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
    ↵↵
    -2.41
    }
    -2.33
     there
    -2.08
    In
    -1.96
     it
    -1.77
    _{
    -1.70
    you
    -1.70
    .,"
    -1.62
     two
    -1.59
    You
    -1.55
    POSITIVE LOGITS
     ของ
    2.11
     nimmer
    2.02
     gefe
    2.00
     consectetur
    1.99
    Natürlich
    1.99
    katalog
    1.92
     ſol
    1.90
     dieťa
    1.88
     them
    1.86
    hej
    1.86
    Activations Density 0.005%

    No Known Activations