© 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. 372
    Prev
    Next
    INDEX
    Explanations

    URL query parameters and assignments

    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
    "
    -2.23
    </h2>
    -2.23
    .
    -2.17
    \
    -2.06
    ↵↵↵↵
    -1.92
    )
    -1.91
    $
    -1.88
    {
    -1.84
    ↵↵↵↵↵↵↵↵↵↵
    -1.70
     not
    -1.67
    POSITIVE LOGITS
    镠
    1.72
    cemos
    1.69
    çou
    1.67
     DÍA
    1.59
     그의
    1.58
    ému
    1.57
     vuotta
    1.57
    antique
    1.57
     xadrez
    1.56
    Ưu
    1.56
    Activations Density 0.009%

    No Known Activations