© 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. 116845
    Prev
    Next
    INDEX
    Explanations

    the back of the human brain

    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
     years
    -0.06
     sculpt
    -0.06
     five
    -0.06
     കോണ്‍
    -0.06
     architects
    -0.06
     বিজ্ঞানীরা
    -0.06
     that
    -0.05
     studio
    -0.05
     eighth
    -0.05
     skeptical
    -0.05
    POSITIVE LOGITS
    หลาย
    0.07
     ponownie
    0.06
    類型
    0.06
     부담
    0.06
     หลาย
    0.06
    elihat
    0.06
     още
    0.06
     തന്നെ
    0.06
     varios
    0.06
     ‎
    0.06
    Activations Density 0.061%

    No Known Activations