© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118679
    Prev
    Next
    INDEX
    Explanations

    Peri- or Cardiac-

    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
     teaming
    -0.06
    БК
    -0.06
     subspace
    -0.06
     teamed
    -0.06
    いく
    -0.06
     twice
    -0.06
     $"{
    -0.05
    estimates
    -0.05
     two
    -0.05
     half
    -0.05
    POSITIVE LOGITS
     旅行
    0.06
     conditions
    0.06
     চাহিদা
    0.06
    conditions
    0.06
    可以通过
    0.06
     através
    0.06
     своей
    0.06
     někter
    0.06
     석
    0.06
    僻
    0.06
    Activations Density 0.001%

    No Known Activations