© 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. 130545
    Prev
    Next
    INDEX
    Explanations

    currency, type, design

    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
     différentes
    -0.07
     different
    -0.07
     différents
    -0.07
     정부
    -0.07
    ἕ
    -0.06
     farklı
    -0.06
    不同的
    -0.06
     diferentes
    -0.06
    異なる
    -0.06
     government
    -0.06
    POSITIVE LOGITS
     foreseen
    0.07
     bahkan
    0.06
     side
    0.06
     Everest
    0.06
     аллер
    0.06
     যোগাযোগ
    0.06
     حتی
    0.06
     even
    0.06
    SystemFileSystem
    0.06
     envisioned
    0.06
    Activations Density 0.005%

    No Known Activations