© 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. 85170
    Prev
    Next
    INDEX
    Explanations

    HTML elements like div, class, image, icon

    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
     than
    -0.98
     comien
    -0.95
    passer
    -0.94
     maksimal
    -0.94
    _{*}
    -0.93
     Frases
    -0.93
     due
    -0.89
    н
    -0.88
     beyond
    -0.88
    <thead>
    -0.87
    POSITIVE LOGITS
    افته
    1.02
    らしいです
    0.98
     것은
    0.98
    uties
    0.96
    urilor
    0.94
    ografía
    0.94
     Mga
    0.94
     two
    0.93
    URANCE
    0.92
    onymes
    0.92
    Activations Density 0.221%

    No Known Activations