© 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. 115981
    Prev
    Next
    INDEX
    Explanations

    JavaScript require statements

    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
     two
    -0.06
     Two
    -0.06
     ustal
    -0.06
     используя
    -0.06
     Elimin
    -0.06
    Taking
    -0.06
     ফ্যাস
    -0.06
     пр
    -0.06
     multiple
    -0.06
    Two
    -0.06
    POSITIVE LOGITS
    炎症
    0.07
     naissance
    0.06
    仍然
    0.06
     kojim
    0.06
     куда
    0.06
    fake
    0.06
     جمال
    0.06
    Naissance
    0.06
     ibu
    0.06
     גע
    0.06
    Activations Density 0.069%

    No Known Activations