© 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. 115844
    Prev
    Next
    INDEX
    Explanations

    mkdir, cd, WORKDIR

    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
     both
    -0.07
     which
    -0.07
     each
    -0.07
     îm
    -0.07
     têm
    -0.06
     যাঁ
    -0.06
     unseren
    -0.06
     jedem
    -0.06
    faith
    -0.06
     வாச
    -0.06
    POSITIVE LOGITS
     கற்க
    0.06
     கெல்
    0.06
    卡
    0.06
     progressivement
    0.06
    出して
    0.06
     முற
    0.06
     Ehr
    0.06
     porque
    0.06
     koska
    0.06
     দৃশ্য
    0.05
    Activations Density 0.002%

    No Known Activations