© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130230
    Prev
    Next
    INDEX
    Explanations

    Egypt

    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
     proti
    -0.07
     Lim
    -0.07
    になった
    -0.06
     VII
    -0.06
     jednak
    -0.06
     イエロー
    -0.06
    دهم
    -0.06
     첫
    -0.06
    /?
    -0.06
     seven
    -0.06
    POSITIVE LOGITS
     within
    0.06
    within
    0.06
     focusing
    0.06
    iyorum
    0.06
    Within
    0.06
     fulfil
    0.05
     இதுபோன்ற
    0.05
    已
    0.05
     আপাতত
    0.05
     fastening
    0.05
    Activations Density 0.006%

    No Known Activations