© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 43748
    Prev
    Next
    INDEX
    Explanations

    asynchronous programming constructs

    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
     discul
    -1.47
     memiliki
    -1.45
     comparte
    -1.38
     permanente
    -1.33
     solidar
    -1.32
     heeft
    -1.31
     dejen
    -1.30
     comien
    -1.28
     kader
    -1.28
     dominante
    -1.27
    POSITIVE LOGITS
     its
    1.76
     Heizung
    1.41
     junger
    1.32
     with
    1.31
     film
    1.23
     extent
    1.17
     antiquities
    1.17
     response
    1.16
    俬
    1.15
     französ
    1.14
    Activations Density 0.009%

    No Known Activations