© 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. 118672
    Prev
    Next
    INDEX
    Explanations

    population-based study

    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
     aika
    -0.07
     raggiung
    -0.07
     tenían
    -0.07
     idő
    -0.07
     what
    -0.07
     jika
    -0.07
     very
    -0.07
    隊
    -0.07
     ਤੇ
    -0.07
    真實
    -0.06
    POSITIVE LOGITS
     belirt
    0.06
     explicitly
    0.06
    §
    0.06
    一句
    0.06
     separat
    0.06
     specifying
    0.05
    পুরা
    0.05
     separately
    0.05
    別に
    0.05
     anderen
    0.05
    Activations Density 0.013%

    No Known Activations