© 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. 127993
    Prev
    Next
    INDEX
    Explanations

    words related to origin and status

    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
     redan
    -0.06
    お待ち
    -0.06
     অধিকাংশই
    -0.06
     Saha
    -0.06
     właśnie
    -0.06
    这也
    -0.06
     நாளை
    -0.06
     நேற்று
    -0.05
     моей
    -0.05
    㶲
    -0.05
    POSITIVE LOGITS
     مختلف
    0.08
     különböző
    0.07
     verschiedenen
    0.06
     sete
    0.06
     different
    0.06
     low
    0.06
     related
    0.06
    ｯ
    0.06
     sociedade
    0.06
     provide
    0.06
    Activations Density 0.007%

    No Known Activations