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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 95481
    Prev
    Next
    INDEX
    Explanations

    database schema and model code

    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_22/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
     this
    -1.18
     have
    -1.14
     exclusivas
    -1.09
     that
    -1.08
     inspiradoras
    -1.07
     joyería
    -1.02
    prnewswire
    -1.01
     inclui
    -0.98
    AxisSize
    -0.98
    věd
    -0.97
    POSITIVE LOGITS
           
    1.11
                         
    1.10
             
    1.07
                      
    1.05
         
    1.05
    充電
    1.05
        
    0.99
     чаще
    0.97
            
    0.97
     چون
    0.96
    Activations Density 0.002%

    No Known Activations