© 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. 118022
    Prev
    Next
    INDEX
    Explanations

    pointer to

    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
    嚣
    -0.07
     ഏറ്റവും
    -0.07
     appreciating
    -0.06
     étab
    -0.06
    ებისთვის
    -0.06
     sockets
    -0.06
     البعض
    -0.06
     niektó
    -0.06
    స్తోంది
    -0.06
     utilizz
    -0.06
    POSITIVE LOGITS
    தமிழ்
    0.07
    after
    0.06
    简单
    0.06
    簡單
    0.06
     simple
    0.06
     einfachen
    0.06
     uncomplicated
    0.06
    并在
    0.06
     jednoduch
    0.06
     spécial
    0.06
    Activations Density 0.007%

    No Known Activations