© 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. 115854
    Prev
    Next
    INDEX
    Explanations

    appellant and respondent

    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
    7
    -0.06
    6
    -0.06
    4
    -0.06
    腳
    -0.06
     ноги
    -0.06
    ន់
    -0.06
    1
    -0.06
     другого
    -0.05
    跷
    -0.05
     Sponge
    -0.05
    POSITIVE LOGITS
     создать
    0.07
     รวมถึง
    0.07
     ಹಾಗೂ
    0.07
     ως
    0.07
     allows
    0.07
    hese
    0.06
     destek
    0.06
     क्यों
    0.06
    atau
    0.06
    cture
    0.06
    Activations Density 0.004%

    No Known Activations