© 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. 116581
    Prev
    Next
    INDEX
    Explanations

    header files and code blocks

    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
     removes
    -0.07
     eliminar
    -0.06
     Wiki
    -0.06
     रखती
    -0.06
     aligns
    -0.06
    なので
    -0.06
    тернет
    -0.06
     eliminates
    -0.06
     !!
    -0.06
     বন্দ
    -0.05
    POSITIVE LOGITS
     actually
    0.08
    などを
    0.07
    }|\
    0.06
    기를
    0.06
     رات
    0.06
    actually
    0.06
     simply
    0.06
     semplicemente
    0.06
     عملکرد
    0.06
     తా
    0.06
    Activations Density 0.002%

    No Known Activations