© 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. 117183
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    不管是
    -0.06
    在我们
    -0.06
    Priority
    -0.06
     নিকটে
    -0.06
    Interpol
    -0.06
    送信
    -0.06
    タイプの
    -0.06
     思
    -0.06
     before
    -0.06
     commonplace
    -0.06
    POSITIVE LOGITS
    inho
    0.07
    ocera
    0.06
     musste
    0.06
     بھارتی
    0.06
     බො
    0.06
     कठिन
    0.06
     Leclerc
    0.05
    letic
    0.05
     HALF
    0.05
    用了
    0.05
    Activations Density 0.001%

    No Known Activations