© 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. 72764
    Prev
    Next
    INDEX
    Explanations

    managing or optimizing outcomes

    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
     with
    -2.47
     three
    -2.42
     one
    -2.03
     four
    -2.03
     two
    -2.02
     six
    -1.97
     all
    -1.88
     five
    -1.77
     through
    -1.73
     for
    -1.70
    POSITIVE LOGITS
     ludicrous
    1.62
     ridiculously
    1.58
    ⏑
    1.57
     letzten
    1.56
     другую
    1.48
    actually
    1.45
     เป็น
    1.45
     avaient
    1.45
    igte
    1.42
     avait
    1.41
    Activations Density 0.096%

    No Known Activations