© 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. 121047
    Prev
    Next
    INDEX
    Explanations

    copyright notices, code, and project summaries

    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
     richieste
    -0.06
     رسمی
    -0.06
     neue
    -0.06
     nové
    -0.06
     scherm
    -0.06
    BuildAction
    -0.06
    という
    -0.05
     chứ
    -0.05
     observatory
    -0.05
    म्यान
    -0.05
    POSITIVE LOGITS
    夫妇
    0.06
     malfunctioning
    0.06
     ailes
    0.06
    Combining
    0.06
     scalability
    0.06
     Feature
    0.06
     Combining
    0.06
    failed
    0.06
     democratic
    0.06
    并未
    0.06
    Activations Density 0.007%

    No Known Activations