© 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. 21
    Prev
    Next
    INDEX
    Explanations

    advertisement words

    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
     to
    -1.42
     in
    -1.30
    了自己
    -1.05
     Catalog
    -1.02
     of
    -0.98
    chain
    -0.94
    ,
    -0.91
     even
    -0.91
     COMPANY
    -0.88
    了自己的
    -0.87
    POSITIVE LOGITS
    During
    1.29
    </h3>
    1.27
    After
    1.18
    Every
    1.17
     Если
    1.16
    就会
    1.16
    我们的
    1.15
    每個
    1.12
     если
    1.12
    Our
    1.12
    Activations Density 0.008%

    No Known Activations