© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 105645
    Prev
    Next
    INDEX
    Explanations

    past actions taken

    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_10/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
     our
    -1.81
    我对
    -1.77
     și
    -1.73
     that
    -1.71
    歃
    -1.63
     reembols
    -1.54
    祧
    -1.52
     reagiert
    -1.49
    ၞ
    -1.49
     红色
    -1.48
    POSITIVE LOGITS
     able
    2.50
        
    1.88
         
    1.64
     mistaken
    1.56
          
    1.55
     and
    1.52
    </h2>
    1.49
     ‘‘
    1.47
    InstrumentedTest
    1.44
       
    1.43
    Activations Density 0.348%

    No Known Activations