© 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. 118352
    Prev
    Next
    INDEX
    Explanations

    sequence start markers

    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
    只
    -0.07
     another
    -0.07
    隻
    -0.07
     tylko
    -0.07
    …….
    -0.06
     тільки
    -0.06
    อีก
    -0.06
    ……..
    -0.06
     druga
    -0.06
     only
    -0.06
    POSITIVE LOGITS
     probablemente
    0.07
     probablement
    0.07
     gj
    0.06
     dotyczące
    0.06
     provavelmente
    0.06
     probabilmente
    0.06
     probably
    0.06
     For
    0.06
     dürfte
    0.06
     in
    0.06
    Activations Density 0.004%

    No Known Activations