© 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. 128208
    Prev
    Next
    INDEX
    Explanations

    ins or serializer

    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
     پیر
    -0.06
     participa
    -0.06
     Indigenous
    -0.06
     Aquí
    -0.06
    যুদ্ধ
    -0.06
    參
    -0.06
    GBuf
    -0.06
    仕事
    -0.06
    身
    -0.06
     능력
    -0.06
    POSITIVE LOGITS
     troubled
    0.08
     like
    0.06
     abolished
    0.06
     lcd
    0.06
    management
    0.06
    bone
    0.06
     પૂ
    0.06
    ക്കളുടെ
    0.06
    executive
    0.06
    arovski
    0.06
    Activations Density 0.005%

    No Known Activations