© 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. 118549
    Prev
    Next
    INDEX
    Explanations

    code block openers and keywords

    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
     />;
    -0.88
     static
    -0.78
    Static
    -0.77
    だし
    -0.76
     obě
    -0.76
     depuis
    -0.74
     زنانه
    -0.74
    ž
    -0.73
    ствен
    -0.71
    そば
    -0.71
    POSITIVE LOGITS
     class
    1.94
    class
    1.93
     then
    0.98
    extension
    0.93
     classe
    0.91
     clase
    0.91
    クラス
    0.88
     enum
    0.88
    enum
    0.84
     kelas
    0.80
    Activations Density 0.001%

    No Known Activations