© 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. 119746
    Prev
    Next
    INDEX
    Explanations

    class type declarations

    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
     Swords
    -0.07
    default
    -0.06
    など
    -0.06
    പ്പെട്ട്
    -0.06
     default
    -0.06
    airo
    -0.06
    می
    -0.06
    non
    -0.06
     vb
    -0.06
     وغيرها
    -0.06
    POSITIVE LOGITS
     test
    0.06
    验证
    0.06
     চেন
    0.06
    ﮟ
    0.06
     niz
    0.06
    جهة
    0.06
     unmistak
    0.05
     Hollywood
    0.05
    每次
    0.05
     закон
    0.05
    Activations Density 0.001%

    No Known Activations