© 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. 130645
    Prev
    Next
    INDEX
    Explanations

    technical nouns and programming concepts

    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
    Listening
    -0.06
     শোনা
    -0.06
     ketentuan
    -0.06
     Congolese
    -0.06
     هنت
    -0.06
    モン
    -0.06
     ça
    -0.06
    渐渐
    -0.06
     comp
    -0.06
    Proto
    -0.06
    POSITIVE LOGITS
     ብዙ
    0.06
    多少
    0.06
    겠지만
    0.06
     tenacious
    0.06
     argued
    0.06
    はこちら
    0.06
    원은
    0.06
     ebenfalls
    0.06
     можно
    0.06
     tiež
    0.06
    Activations Density 0.034%

    No Known Activations