© 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. 128160
    Prev
    Next
    INDEX
    Explanations

    question prompts

    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
    用に
    -0.06
    天天
    -0.06
     নিত্য
    -0.06
     diariamente
    -0.06
     τότε
    -0.06
    達
    -0.06
     Critical
    -0.06
    時には
    -0.05
     Phrases
    -0.05
     then
    -0.05
    POSITIVE LOGITS
    Minutes
    0.07
     ايجاد
    0.07
     need
    0.07
     komfort
    0.06
     δή
    0.06
     ایجاد
    0.06
     comforted
    0.06
     really
    0.06
     sekitar
    0.06
     proposed
    0.06
    Activations Density 0.001%

    No Known Activations