© 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. 118975
    Prev
    Next
    INDEX
    Explanations

    University of, this invention, Carcinosarcoma

    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
    考虑
    -0.08
     before
    -0.08
     constitutes
    -0.07
     trước
    -0.07
     dış
    -0.06
     sebelum
    -0.06
     aggrieved
    -0.06
     قبل
    -0.06
     לפני
    -0.06
     čin
    -0.06
    POSITIVE LOGITS
     곳
    0.07
     arbete
    0.06
     versões
    0.06
     value
    0.06
    传承
    0.06
     frail
    0.06
     trust
    0.05
     spill
    0.05
     toric
    0.05
     работа
    0.05
    Activations Density 0.001%

    No Known Activations