© 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. 120237
    Prev
    Next
    INDEX
    Explanations

    DNS and DKIM configuration

    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
    ouvoir
    -0.08
     trzech
    -0.06
    筛
    -0.06
     선정
    -0.06
     comuni
    -0.06
     Drei
    -0.06
    THREE
    -0.06
     dwóch
    -0.06
     الثلاث
    -0.06
     hắn
    -0.06
    POSITIVE LOGITS
    items
    0.07
     পরিকল্পনা
    0.07
     events
    0.06
     inputs
    0.06
    従って
    0.06
     items
    0.06
    inputs
    0.06
    詳しい
    0.06
     consigned
    0.06
     Items
    0.06
    Activations Density 0.004%

    No Known Activations