© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 116051
    Prev
    Next
    INDEX
    Explanations

    government agencies and departments

    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
    Negative Logits
    un
    -0.06
    ,
    -0.06
    ,\
    -0.06
    类似于
    -0.06
    と考えられる
    -0.06
    ības
    -0.05
     TOC
    -0.05
     roughly
    -0.05
    System
    -0.05
    ","
    -0.05
    POSITIVE LOGITS
     ফ্লাই
    0.08
     ఆమె
    0.07
    菄
    0.06
     هر
    0.06
    thereum
    0.06
    diamonds
    0.06
     podium
    0.06
    witch
    0.06
     отвеча
    0.06
     नाटक
    0.06
    Activations Density 0.005%

    No Known Activations