© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107769
    Prev
    Next
    INDEX
    Explanations

    Question prefix

    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
     lamang
    -0.98
    Transk
    -0.94
    Lyric
    -0.92
     лёг
    -0.88
    ĝo
    -0.88
    💽
    -0.86
     montrent
    -0.84
    וּ
    -0.83
     дуже
    -0.82
    球队
    -0.82
    POSITIVE LOGITS
                              
    1.05
                          
    1.02
                                  
    1.00
                      
    0.97
    umpulkan
    0.95
    Yep
    0.93
                         
    0.93
    wikimedia
    0.91
                           
    0.91
                   
    0.90
    Activations Density 0.000%

    No Known Activations