© 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. 103508
    Prev
    Next
    INDEX
    Explanations

    code block delimiters and results

    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
     for
    -1.01
    From
    -0.96
     whenever
    -0.94
     himself
    -0.91
     within
    -0.91
     From
    -0.90
     During
    -0.88
    Either
    -0.88
     beneath
    -0.86
     throughout
    -0.85
    POSITIVE LOGITS
    结果
    1.13
     should
    1.07
    should
    1.04
     '=',
    1.02
     output
    0.97
    应该
    0.96
     будет
    0.94
     will
    0.94
     ==
    0.94
     =>
    0.92
    Activations Density 0.063%

    No Known Activations