© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68407
    Prev
    Next
    INDEX
    Explanations

    knock compounds and phrases

    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
     Of
    -2.23
                    
    -2.11
    都不知道
    -2.05
          
    -2.03
    </h1>
    -2.00
                            
    -1.95
     häufigsten
    -1.88
                                
    -1.87
     muitos
    -1.84
     會
    -1.84
    POSITIVE LOGITS
     \&
    2.33
    ‌ها
    1.98
    檍
    1.91
    warnai
    1.88
     sabid
    1.86
     Arrest
    1.84
    spanning
    1.81
    鼇
    1.81
    ...");
    1.79
     escuro
    1.79
    Activations Density 0.006%

    No Known Activations