© 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. 34-GEMMASCOPE-RES-131K
    4. 109575
    Prev
    Next
    INDEX
    Explanations

    Windows 7

    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_34/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
    数据库
    -0.98
    чів
    -0.90
    nyx
    -0.89
    データベース
    -0.85
     proteína
    -0.84
    喉
    -0.84
    niť
    -0.83
    riebene
    -0.82
    makeConstraints
    -0.81
    чья
    -0.81
    POSITIVE LOGITS
     Windows
    3.06
    Windows
    2.30
     Microsoft
    2.00
     windows
    1.87
    windows
    1.66
     Win
    1.62
    Microsoft
    1.61
    WINDOWS
    1.53
    microsoft
    1.50
     Window
    1.43
    Activations Density 0.283%

    No Known Activations