© 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. 116098
    Prev
    Next
    INDEX
    Explanations

    returning or repeating

    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
    Not in Any Lists

    No Comments

    Negative Logits
     الحالي
    -0.07
    garn
    -0.06
     current
    -0.06
     MINI
    -0.06
     ukon
    -0.06
     huidige
    -0.06
     lå
    -0.06
     Mini
    -0.06
     최근
    -0.06
     podrás
    -0.06
    POSITIVE LOGITS
     kembali
    0.08
     volver
    0.07
     retorna
    0.07
     vuelva
    0.06
     retorno
    0.06
    次回
    0.06
     ritor
    0.06
     tornare
    0.06
     terug
    0.06
     returns
    0.06
    Activations Density 0.081%

    No Known Activations