© 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. 19197
    Prev
    Next
    INDEX
    Explanations

    mixed language programming and technical terms

    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
    骜
    -2.59
    ,”
    -2.36
     pleas
    -2.34
    ’,
    -2.27
     регулярно
    -2.25
    鬟
    -2.25
     charismatic
    -2.23
    愎
    -2.19
    ↵
    -2.19
    驁
    -2.17
    POSITIVE LOGITS
    ing
    2.50
     IBOutlet
    2.50
    啬
    2.45
     Of
    2.44
     tens
    2.44
    u
    2.41
    鹛
    2.39
    .
    2.38
    ة
    2.33
    دواج
    2.28
    Activations Density 0.001%

    No Known Activations