© 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. 119532
    Prev
    Next
    INDEX
    Explanations

    Haixiu, Activision, SHARK, With

    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
     протяжении
    -0.07
     విష
    -0.06
     ошибки
    -0.06
     తిరిగి
    -0.06
    寒い
    -0.06
    Taxi
    -0.06
     wales
    -0.06
    过程中
    -0.06
     صحبت
    -0.06
     잘못
    -0.06
    POSITIVE LOGITS
    inspiring
    0.06
     clearing
    0.06
     නිර්
    0.06
     thriller
    0.06
     minimalism
    0.06
     быстро
    0.06
     unleashing
    0.06
     подходя
    0.06
     contemplating
    0.06
     really
    0.06
    Activations Density 0.004%

    No Known Activations