© 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. 10-GEMMASCOPE-RES-131K
    7. 100445
    Prev
    Next
    INDEX
    Explanations

    directly and its context

    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
                
    -1.60
    ("
    -1.59
     ALSO
    -1.53
                       
    -1.52
              
    -1.51
                 
    -1.49
                  
    -1.48
          
    -1.48
     في
    -1.45
             
    -1.44
    POSITIVE LOGITS
     directly
    2.17
     direct
    1.90
    Direct
    1.79
     diretto
    1.72
     direta
    1.70
     Directly
    1.69
    directly
    1.62
    direct
    1.59
     diretta
    1.59
     Direct
    1.55
    Activations Density 0.075%

    No Known Activations