© 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. 116883
    Prev
    Next
    INDEX
    Explanations

    is known as

    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
     olmadığını
    -0.06
    迵
    -0.06
    Through
    -0.06
     olduğunu
    -0.06
    در
    -0.06
     menimbulkan
    -0.06
     periodic
    -0.06
    Does
    -0.05
     query
    -0.05
     याद
    -0.05
    POSITIVE LOGITS
     prepares
    0.07
     improves
    0.07
     fornece
    0.06
     then
    0.06
     consists
    0.06
     increases
    0.06
     fornecer
    0.06
     strate
    0.06
     müm
    0.06
     দুপুরে
    0.06
    Activations Density 0.169%

    No Known Activations