© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120655
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Volume
    -0.06
     sedang
    -0.06
     выбирать
    -0.06
     gewählt
    -0.06
     مطابق
    -0.06
     scelto
    -0.05
    ський
    -0.05
    ভিতে
    -0.05
    一大
    -0.05
     economico
    -0.05
    POSITIVE LOGITS
     procent
    0.06
     Lease
    0.06
     ಕರಿ
    0.06
     Kirchner
    0.06
     Geschichte
    0.06
     inspectors
    0.06
     hag
    0.06
    比較
    0.06
     few
    0.06
     gard
    0.06
    Activations Density 0.000%

    No Known Activations