© 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. 128292
    Prev
    Next
    INDEX
    Explanations

    code comments and structure

    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
     by
    -0.08
     extrapol
    -0.07
     contemplation
    -0.06
     immunos
    -0.06
     Monika
    -0.06
     Initiate
    -0.06
     allevi
    -0.06
     alten
    -0.06
     transporter
    -0.06
    archives
    -0.06
    POSITIVE LOGITS
    ध्
    0.06
     Sham
    0.05
     metoda
    0.05
    ft
    0.05
    Sham
    0.05
    一部分
    0.05
    今日も
    0.05
    locally
    0.05
     পেরিয়ে
    0.05
     additions
    0.05
    Activations Density 0.001%

    No Known Activations