© 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. 913
    Prev
    Next
    INDEX
    Explanations

    introductions and lists

    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
    </h2>
    -2.55
     “
    -1.77
    ’
    -1.65
    ”).
    -1.61
    .
    -1.52
    ↵
    -1.50
    </blockquote>
    -1.48
    </strong>
    -1.45
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.45
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    -1.45
    POSITIVE LOGITS
    桄
    2.02
     mantan
    1.79
     murió
    1.67
    ༀ
    1.65
    猥
    1.63
     murieron
    1.61
     Cię
    1.59
    ଃ
    1.57
    杙
    1.57
    珖
    1.56
    Activations Density 0.013%

    No Known Activations