© 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. 130080
    Prev
    Next
    INDEX
    Explanations

    maximal values

    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
    耂
    -0.06
    㱛
    -0.06
     specified
    -0.06
     বিজেপি
    -0.06
     moderate
    -0.06
    㽞
    -0.06
    meme
    -0.06
     spite
    -0.06
    にて
    -0.06
     decreed
    -0.06
    POSITIVE LOGITS
     هنوز
    0.06
    通常
    0.06
     ainda
    0.06
     концентра
    0.06
    ="<?
    0.06
     обычно
    0.06
     fordul
    0.06
    角落
    0.06
     सिल्
    0.05
     Hats
    0.05
    Activations Density 0.022%

    No Known Activations