© 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. 64104
    Prev
    Next
    INDEX
    Explanations

    addresses and affiliations

    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
    dü
    -0.93
    recover
    -0.93
    {"{
    -0.89
    توض
    -0.87
    NSYLVANIA
    -0.84
     ciclismo
    -0.84
    我对
    -0.84
    getType
    -0.83
     faltar
    -0.83
     except
    -0.82
    POSITIVE LOGITS
      
    1.88
       
    1.58
        
    1.38
          
    0.99
              
    0.93
                      
    0.90
                  
    0.85
     gud
    0.84
     LCCN
    0.83
            
    0.82
    Activations Density 0.010%

    No Known Activations