© 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. 55852
    Prev
    Next
    INDEX
    Explanations

    method calls with parentheses

    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
     siyang
    -0.98
    鍍
    -0.94
    これらの
    -0.93
    韌
    -0.90
    自立
    -0.87
     Estos
    -0.87
    〚
    -0.85
    These
    -0.82
     विश्वसनीय
    -0.81
    に入った
    -0.80
    POSITIVE LOGITS
     null
    1.98
     new
    1.96
    null
    1.75
     false
    1.62
    new
    1.57
    false
    1.56
    true
    1.55
     true
    1.52
     новый
    1.34
     "",
    1.27
    Activations Density 0.007%

    No Known Activations