© 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. 128019
    Prev
    Next
    INDEX
    Explanations

    place names or brands with following words

    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
    durante
    -1.51
    فقط
    -1.45
    Là
    -1.38
    Lors
    -1.35
    بله
    -1.30
    Enfin
    -1.23
    Dès
    -1.23
    Télécharger
    -1.22
    خود
    -1.22
    Où
    -1.22
    POSITIVE LOGITS
                 
    1.40
        
    1.39
              
    1.38
                
    1.37
               
    1.36
     deaktivi
    1.33
           
    1.33
    tabol
    1.30
                                   
    1.29
                       
    1.26
    Activations Density 0.138%

    No Known Activations