© 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. 117637
    Prev
    Next
    INDEX
    Explanations

    directions

    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
    包括
    -0.07
     بعد
    -0.06
     รวม
    -0.06
     ولم
    -0.06
     Maeda
    -0.06
     baos
    -0.06
     sebelum
    -0.06
     before
    -0.06
    .//
    -0.06
     including
    -0.06
    POSITIVE LOGITS
     Programming
    0.06
     HUGE
    0.06
    ப்புற
    0.06
     huge
    0.06
    riendo
    0.06
     másik
    0.05
     Ö
    0.05
     constitu
    0.05
     огром
    0.05
     programming
    0.05
    Activations Density 0.002%

    No Known Activations