© 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. 120943
    Prev
    Next
    INDEX
    Explanations

    parenthetical explanations

    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
     satin
    -0.07
     chiaro
    -0.06
     Rectangle
    -0.06
     može
    -0.06
     chắc
    -0.06
    typically
    -0.06
     ممکن
    -0.06
    يمكن
    -0.06
     really
    -0.06
    可能会
    -0.06
    POSITIVE LOGITS
    த்திலிருந்து
    0.06
     has
    0.06
     or
    0.06
    Has
    0.06
    相互
    0.06
     from
    0.06
    类似的
    0.06
    右
    0.06
     новую
    0.05
    对
    0.05
    Activations Density 0.015%

    No Known Activations