© 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. 90704
    Prev
    Next
    INDEX
    Explanations

    fields and defs

    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
     by
    -1.52
     penggunaan
    -1.42
     even
    -1.37
     using
    -1.30
    ません
    -1.29
     zelfs
    -1.29
     or
    -1.28
    できません
    -1.24
     
    -1.23
    途径
    -1.21
    POSITIVE LOGITS
    ཌ
    1.63
     ۱۴۰۰
    1.63
     raça
    1.61
     poë
    1.58
     Werken
    1.55
     forcément
    1.52
    weder
    1.52
     パック
    1.50
    この
    1.48
     ۱۳۹
    1.48
    Activations Density 0.001%

    No Known Activations