© 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. 117208
    Prev
    Next
    INDEX
    Explanations

    Malawi, Garden, Eel

    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
    每
    -0.07
    لاح
    -0.06
    )[
    -0.06
     setiap
    -0.06
    を行い
    -0.06
     тысяч
    -0.06
     Каждый
    -0.06
     प्रत्येक
    -0.06
     ogni
    -0.06
     всеки
    -0.06
    POSITIVE LOGITS
     imaginative
    0.06
     enthous
    0.06
    oue
    0.06
     lovable
    0.06
     kiz
    0.06
    ION
    0.06
     Drs
    0.06
     eclectic
    0.06
     enthusiastic
    0.06
     disk
    0.06
    Activations Density 0.001%

    No Known Activations