© 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. 129093
    Prev
    Next
    INDEX
    Explanations

    music kits, artists, remixers

    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
    🤮
    -0.07
     узнать
    -0.06
     dicho
    -0.06
     deutschen
    -0.06
    cun
    -0.06
     appla
    -0.06
    बास
    -0.06
    dates
    -0.06
    🙀
    -0.06
    不说
    -0.05
    POSITIVE LOGITS
     made
    0.07
     youthful
    0.07
     siguiendo
    0.06
     by
    0.06
     envej
    0.06
     Aspects
    0.06
     خاصيه
    0.06
    клю
    0.06
     যাচ্ছি
    0.06
    Part
    0.06
    Activations Density 0.004%

    No Known Activations