© 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. 128001
    Prev
    Next
    INDEX
    Explanations

    code and markup beginnings

    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
    Negative Logits
    अपने
    -0.06
     każdej
    -0.06
     worldly
    -0.06
    Hei
    -0.06
     tama
    -0.05
    MT
    -0.05
    ⊱
    -0.05
    www
    -0.05
     রহমানের
    -0.05
     remorse
    -0.05
    POSITIVE LOGITS
     in
    0.07
     the
    0.07
     as
    0.07
     ausdr
    0.06
     xuất
    0.06
     there
    0.06
     it
    0.06
     nghiên
    0.06
     предложи
    0.06
     аргу
    0.06
    Activations Density 0.004%

    No Known Activations