© 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. 65281
    Prev
    Next
    INDEX
    Explanations

    describing attributes or capabilities

    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
     this
    -1.49
     their
    -1.46
     it
    -1.42
     nahezu
    -1.32
     almost
    -1.32
     without
    -1.30
     nästan
    -1.26
     ungefär
    -1.23
     verkligen
    -1.23
    lierten
    -1.21
    POSITIVE LOGITS
    amaño
    1.24
    ROY
    1.21
    beten
    1.20
    dő
    1.19
    ærer
    1.17
     tenemos
    1.17
     Kinh
    1.17
    mainAxisSize
    1.16
    יש
    1.16
     gás
    1.16
    Activations Density 0.088%

    No Known Activations