© 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-3-12B
    5. 24-GEMMASCOPE-2-RES-16K
    7. 5823
    Prev
    Next
    INDEX
    Explanations

    conjunctions and separators

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_24_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝚋
    0.49
    these
    0.49
     Harrow
    0.48
     উৎসাহ
    0.46
    ুহ
    0.45
     Carvalho
    0.45
    нуу
    0.45
    ご注文
    0.45
     destes
    0.45
    тара
    0.44
    POSITIVE LOGITS
                          
    0.56
    、
    0.54
                         
    0.51
                              
    0.51
                       
    0.50
                            
    0.50
                               
    0.50
                           
    0.50
                                
    0.50
                             
    0.50
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.