© 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. 34-GEMMASCOPE-RES-131K
    7. 33485
    Prev
    Next
    INDEX
    Explanations

    using System namespace class

    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
     Oaks
    -0.84
     Ahora
    -0.82
    quelize
    -0.78
    ActiveRecord
    -0.76
    usei
    -0.76
    ᆯ
    -0.75
     ال
    -0.73
    itor
    -0.72
    资
    -0.71
    下一步
    -0.71
    POSITIVE LOGITS
     class
    1.55
    class
    1.53
    public
    1.35
    namespace
    1.18
     public
    1.05
    Class
    0.96
    Console
    0.86
     ロゴ
    0.85
     Class
    0.84
    shy
    0.83
    Activations Density 0.013%

    No Known Activations