© 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. 11272
    Prev
    Next
    INDEX
    Explanations

    URLs and code snippets

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

    structured metadata and formatting elements in technical documents, such as URLs, timestamps, institutional affiliations, and document identifiers.

    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
    zaron
    -1.43
    két
    -1.40
    voller
    -1.37
     ребенку
    -1.34
    算了
    -1.34
     bude
    -1.31
     zorg
    -1.30
    亲爱的
    -1.30
     lados
    -1.29
     frio
    -1.29
    POSITIVE LOGITS
    Zubereitung
    1.39
    味わい
    1.32
    Informationen
    1.30
     anledning
    1.30
     dále
    1.29
    便捷
    1.27
     selepas
    1.26
     ビジネス
    1.25
    之时
    1.25
     unless
    1.23
    Activations Density 0.112%

    No Known Activations