© 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. 116001
    Prev
    Next
    INDEX
    Explanations

    setContentView or super.onCreate

    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
    /
    -0.09
    ,
    -0.07
    也都
    -0.06
     toegang
    -0.06
     जुटा
    -0.06
    还有
    -0.06
    還有
    -0.06
    アクセ
    -0.06
     resaltar
    -0.06
    जेक्शन
    -0.05
    POSITIVE LOGITS
     deserves
    0.06
    determine
    0.06
    дин
    0.06
     moment
    0.06
    常常
    0.06
     deserving
    0.06
     "?"
    0.06
     deserve
    0.06
    আমাকে
    0.06
     අය
    0.05
    Activations Density 0.001%

    No Known Activations