© 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. 110651
    Prev
    Next
    INDEX
    Explanations

    Reactive programming concepts

    np_acts-logits-general · gemini-2.5-flash-lite

    reactive programming library names and classes (like RxSwift, ReactiveSwift, Observer, Observable).

    oai_token-act-pair · claude-4-5-sonnetTriggered by @bfgcn7frf5
    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
     fragte
    -1.50
    {
    -1.40
    线的
    -1.34
     这
    -1.26
    缺点
    -1.25
    禊
    -1.24
    osť
    -1.21
    zość
    -1.21
    …”
    -1.20
    。
    -1.20
    POSITIVE LOGITS
     pleas
    1.48
    лись
    1.40
     rápidamente
    1.38
    <td>
    1.34
     this
    1.28
    </b>
    1.27
     your
    1.27
    薷
    1.27
    屛
    1.27
    ència
    1.26
    Activations Density 0.008%

    No Known Activations