© 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. 112243
    Prev
    Next
    INDEX
    Explanations

    Android UI layouts

    np_acts-logits-general · gemini-2.5-flash-lite

    the opening tags of container elements in code, particularly in XML and HTML layouts.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     the
    -1.55
     and
    -1.48
     be
    -1.43
    
    -1.24
    ai
    -1.24
    核心
    -1.21
    ita
    -1.20
    š
    -1.20
    isk
    -1.20
    hell
    -1.20
    POSITIVE LOGITS
    予定です
    1.77
    Fornecedor
    1.34
    还不是
    1.32
    เย็น
    1.31
    Possibly
    1.29
     яких
    1.27
     fumée
    1.27
     pourront
    1.27
    Empleado
    1.26
     fortfarande
    1.23
    Activations Density 0.011%

    No Known Activations