© 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. 102191
    Prev
    Next
    INDEX
    Explanations

    musical prelude, coda, or segue

    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
     o
    -2.88
    也在
    -2.39
    ны
    -2.33
    獓
    -2.06
    re
    -2.06
    祧
    -2.05
     que
    -2.03
    ↵↵
    -2.03
     podem
    -2.03
    ῞
    -2.02
    POSITIVE LOGITS
    replyreport
    2.41
    ⦊
    2.28
    on
    2.16
    しては
    2.05
     先生
    2.05
     Addressing
    2.02
    ۠
    1.97
     bedoeld
    1.95
     pembun
    1.95
     Placing
    1.95
    Activations Density 0.004%

    No Known Activations