© 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. 60914
    Prev
    Next
    INDEX
    Explanations

    caribbean Sea, zone, tropical, winter, country

    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
    9
    -2.77
    𓐍
    -2.59
    </h3>
    -2.52
     ส์
    -2.50
    1
    -2.47
     correta
    -2.38
    饪
    -2.38
     gewisse
    -2.36
     respostas
    -2.28
     BEFORE
    -2.27
    POSITIVE LOGITS
     exquisite
    2.66
     vader
    2.61
     собака
    2.53
     multifaceted
    2.42
    換え
    2.42
     innovative
    2.39
     ".";
    2.39
     ingenious
    2.38
    vantaged
    2.34
     nahezu
    2.25
    Activations Density 0.005%

    No Known Activations