© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 12218
    Prev
    Next
    INDEX
    Explanations

    global scope

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

    words indicating widespread or global scope, particularly "everywhere," "across," "worldwide," and similar terms denoting broad geographic distribution.

    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
     for
    -2.50
     by
    -1.95
     &
    -1.93
     or
    -1.92
     with
    -1.68
     if
    -1.61
     has
    -1.57
     so
    -1.56
     a
    -1.52
     two
    -1.42
    POSITIVE LOGITS
     availa
    1.48
    ఱ
    1.48
    partimento
    1.48
    complish
    1.47
    apka
    1.46
    lowing
    1.42
    commod
    1.38
     ajouter
    1.37
     olabilir
    1.36
    
    1.34
    Activations Density 0.033%

    No Known Activations