© 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. 22-GEMMASCOPE-RES-131K
    7. 98271
    Prev
    Next
    INDEX
    Explanations

    demonstration, example, testcase

    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_22/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
    ּוֹ
    -1.16
    之际
    -1.07
    ִּ
    -1.04
     detalló
    -1.02
     Determination
    -1.00
    +:+
    -0.99
    ēd
    -0.98
    ַּ
    -0.97
    biť
    -0.95
    tonsoft
    -0.95
    POSITIVE LOGITS
     demonstration
    1.28
     experiment
    1.23
     demonstrations
    1.17
     example
    1.12
     examples
    1.11
     test
    1.10
     demonstrate
    1.09
     tester
    1.06
    demon
    1.03
    演示
    1.02
    Activations Density 0.083%

    No Known Activations