© 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. 20403
    Prev
    Next
    INDEX
    Explanations

    covers topics and ranges

    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
     about
    -1.58
     there
    -1.26
     only
    -1.24
    .
    -1.22
    的结果
    -1.19
    搆
    -1.18
     even
    -1.16
    ophageal
    -1.13
     helping
    -1.13
     two
    -1.12
    POSITIVE LOGITS
     covered
    1.80
     covers
    1.70
     cover
    1.55
     COVER
    1.48
     mencakup
    1.45
     coverage
    1.38
     covering
    1.33
    Covered
    1.32
     folgender
    1.32
    轳
    1.27
    Activations Density 0.044%

    No Known Activations