© 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. 12491
    Prev
    Next
    INDEX
    Explanations

    foreign words or phrases

    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
    というわけで
    -2.14
    notated
    -1.92
    揹
    -1.89
    푠
    -1.84
    などを
    -1.80
    這麼
    -1.78
    以上です
    -1.78
    余談
    -1.78
    聖誕
    -1.77
    すば
    -1.75
    POSITIVE LOGITS
     olvidar
    1.96
     stato
    1.87
    逻
    1.85
     Voraussetzungen
    1.84
    𝒛
    1.83
    
    1.80
    赑
    1.80
     ollut
    1.74
     тех
    1.74
     è
    1.73
    Activations Density 0.035%

    No Known Activations