© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 118466
    Prev
    Next
    INDEX
    Explanations

    printed editions and historical texts

    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
    已經
    -0.07
     artık
    -0.07
    已经
    -0.07
    早已
    -0.07
     znacznie
    -0.07
    すでに
    -0.06
     perintah
    -0.06
     अत्यधिक
    -0.06
     již
    -0.06
    各地
    -0.06
    POSITIVE LOGITS
    ;
    0.06
     другая
    0.06
    ;"
    0.06
     социально
    0.05
     sitcom
    0.05
    ώντας
    0.05
     helping
    0.05
     claiming
    0.05
     Member
    0.05
     чтобы
    0.05
    Activations Density 0.004%

    No Known Activations