© 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. 3618
    Prev
    Next
    INDEX
    Explanations

    copyright notices and licenses

    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
    byshire
    -1.69
    brać
    -1.68
    Yeni
    -1.67
     丼
    -1.67
    dubbo
    -1.66
    弒
    -1.64
    درب
    -1.63
     veya
    -1.63
    Sejarah
    -1.62
     kabát
    -1.61
    POSITIVE LOGITS
     it
    1.92
    </strong>
    1.79
     possessing
    1.74
    </h1>
    1.68
    汭
    1.66
     presently
    1.65
     
    1.61
    ↵
    1.59
    到时候
    1.59
    ng
    1.57
    Activations Density 0.001%

    No Known Activations