© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 119699
    Prev
    Next
    INDEX
    Explanations

    code structure definitions

    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
    Для
    -0.07
     после
    -0.07
    После
    -0.07
     після
    -0.07
    These
    -0.07
     После
    -0.07
     উপযোগী
    -0.06
    Эти
    -0.06
    After
    -0.06
     для
    -0.06
    POSITIVE LOGITS
    şu
    0.06
     comandos
    0.06
     another
    0.06
    egang
    0.06
     papers
    0.06
     proactive
    0.06
     curr
    0.06
     vigilant
    0.06
     committed
    0.05
    ua
    0.05
    Activations Density 0.001%

    No Known Activations