© 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. 129285
    Prev
    Next
    INDEX
    Explanations

    data type and class definitions

    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
    具体的な
    -0.07
    合計
    -0.06
     emphasise
    -0.06
     экземпля
    -0.06
    或者是
    -0.06
     DIRECTOR
    -0.06
     ornate
    -0.06
    ಾಗ್
    -0.06
     केवल
    -0.06
     insieme
    -0.06
    POSITIVE LOGITS
     गलत
    0.06
     miscon
    0.06
     though
    0.06
     වල
    0.05
     our
    0.05
     മറ്റൊരു
    0.05
    CAT
    0.05
    ਰ
    0.05
    ก่อน
    0.05
     আশ্চর্য
    0.05
    Activations Density 0.001%

    No Known Activations