© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120733
    Prev
    Next
    INDEX
    Explanations

    lists ending with 'and the like' or containing foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/gemma-4-saes/gemma-4-31b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    是指
    -0.07
    不仅仅
    -0.07
    有利于
    -0.06
     시험
    -0.06
     Libraries
    -0.06
    能够在
    -0.06
     generations
    -0.06
    进一步
    -0.06
    一方面
    -0.06
     गोल्डन
    -0.06
    POSITIVE LOGITS
     physiologic
    0.06
      
    0.05
     абсолютно
    0.05
     threes
    0.05
     cheery
    0.05
     একদম
    0.05
    akova
    0.05
    
    0.05
    nbsp
    0.05
     appunto
    0.05
    Activations Density 0.013%

    No Known Activations