© 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. 34-GEMMASCOPE-RES-131K
    7. 94181
    Prev
    Next
    INDEX
    Explanations

    Mornington, Lossless, Star Wars, Computer Science

    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_34/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
     on
    -1.98
     those
    -1.77
     had
    -1.73
     should
    -1.70
     two
    -1.69
     even
    -1.66
     an
    -1.65
     with
    -1.65
     one
    -1.63
     in
    -1.58
    POSITIVE LOGITS
     美丽
    1.56
     AMAZING
    1.45
     ซึ่ง
    1.42
    禟
    1.39
     также
    1.38
     REALLY
    1.38
     汽车
    1.37
    during
    1.37
     morire
    1.36
     Dinas
    1.35
    Activations Density 0.303%

    No Known Activations