© 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. 118532
    Prev
    Next
    INDEX
    Explanations

    new developments

    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
     अक्सर
    -0.07
     обычно
    -0.06
     હજાર
    -0.06
     gebruiken
    -0.06
     school
    -0.06
     includ
    -0.06
     čak
    -0.06
     herkes
    -0.06
     generalmente
    -0.06
     hijo
    -0.06
    POSITIVE LOGITS
     새로운
    0.08
     new
    0.08
     yeni
    0.07
    新的
    0.07
    new
    0.07
     nuevas
    0.07
     nuove
    0.07
     பழைய
    0.07
     नए
    0.07
     новых
    0.07
    Activations Density 0.101%

    No Known Activations