© 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. 39294
    Prev
    Next
    INDEX
    Explanations

    Taxi Text

    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
     baden
    -1.72
    睃
    -1.68
     magnific
    -1.63
     kreuz
    -1.63
     gela
    -1.62
    ↵↵
    -1.62
     เป็น
    -1.61
    摀
    -1.59
     wonderfully
    -1.55
     delightfully
    -1.55
    POSITIVE LOGITS
     more
    2.36
     one
    2.28
    There
    1.93
     Even
    1.88
     not
    1.85
    After
    1.84
     While
    1.83
    During
    1.82
     two
    1.82
     there
    1.80
    Activations Density 0.006%

    No Known Activations