© 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. 120801
    Prev
    Next
    INDEX
    Explanations

    computer package feed input

    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
     وكل
    -0.06
    Эти
    -0.06
     अॅ
    -0.06
     prototype
    -0.06
    verting
    -0.06
    MENU
    -0.06
     bijective
    -0.06
     உள்ளது
    -0.06
     antiquated
    -0.05
     ćete
    -0.05
    POSITIVE LOGITS
     guise
    0.06
    មិន
    0.06
    周
    0.06
     не
    0.06
    是否有
    0.06
    チン
    0.06
     ندارد
    0.06
     нього
    0.06
    日
    0.06
     कैम
    0.05
    Activations Density 0.001%

    No Known Activations