© 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. 128990
    Prev
    Next
    INDEX
    Explanations

    work and living

    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
    ového
    -0.06
    También
    -0.06
     consider
    -0.06
     design
    -0.06
    ρία
    -0.06
    ហ
    -0.06
     محس
    -0.06
     también
    -0.06
     haemorrh
    -0.06
    不过
    -0.06
    POSITIVE LOGITS
     Possible
    0.07
     Ergebn
    0.06
     Trabalho
    0.06
    imo
    0.06
     wakati
    0.06
     কাজের
    0.06
     beinhaltet
    0.06
    仕事を
    0.06
    Britain
    0.06
     mảnh
    0.06
    Activations Density 0.017%

    No Known Activations