© 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. 105972
    Prev
    Next
    INDEX
    Explanations

    assigning web element property values

    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
    他們
    -1.65
     Mereka
    -1.63
     они
    -1.59
     вони
    -1.53
     eux
    -1.39
     metav
    -1.36
     ()
    -1.36
     них
    -1.35
    wyczaj
    -1.33
     ihnen
    -1.30
    POSITIVE LOGITS
     are
    1.87
     is
    1.87
     were
    1.61
     to
    1.42
     &
    1.38
     would
    1.33
     describe
    1.27
     in
    1.23
     as
    1.23
     perfetto
    1.21
    Activations Density 0.013%

    No Known Activations