© 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. 130658
    Prev
    Next
    INDEX
    Explanations

    Basic Graphics

    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
    所以
    -0.07
     but
    -0.07
     new
    -0.06
     not
    -0.06
     longtime
    -0.06
     seven
    -0.06
     зависит
    -0.06
    Está
    -0.06
    但在
    -0.06
     reinvigor
    -0.06
    POSITIVE LOGITS
     Concrete
    0.06
     बनाई
    0.06
    㗊
    0.06
     repart
    0.05
     그래도
    0.05
    bundled
    0.05
     tapping
    0.05
    แก้ไข
    0.05
     concrete
    0.05
     Awesome
    0.05
    Activations Density 0.014%

    No Known Activations