© 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. 128289
    Prev
    Next
    INDEX
    Explanations

    code types

    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
    になりました
    -0.07
     после
    -0.07
     após
    -0.06
     datang
    -0.06
     après
    -0.06
     периоди
    -0.06
     dopo
    -0.06
     यादव
    -0.06
    жди
    -0.06
    निश्
    -0.06
    POSITIVE LOGITS
     That
    0.06
     تمامی
    0.06
    每一个
    0.06
    每一個
    0.06
     iedere
    0.06
     DJs
    0.05
     ア
    0.05
    所有的
    0.05
    每一
    0.05
    يمه
    0.05
    Activations Density 0.001%

    No Known Activations