© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 1011
    Prev
    Next
    INDEX
    Explanations

    speed, free, unique id

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     例文帳に追加
    0.74
    hasOwnProperty
    0.72
     соответствующие
    0.71
    私募基金管理人
    0.71
    することができる
    0.71
     беременности
    0.69
    Ã
    0.67
    中华人民共和国
    0.67
    �
    0.66
    SimpleDateFormat
    0.65
    POSITIVE LOGITS
              
    1.61
               
    1.59
             
    1.54
                 
    1.53
                  
    1.48
                   
    1.44
                
    1.39
    …………
    1.36
                     
    1.36
    …………..
    1.35
    Activations Density 0.352%

    No Known Activations