© 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. 120503
    Prev
    Next
    INDEX
    Explanations

    research study methodology

    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
    ímica
    -0.06
     provoquer
    -0.06
     tested
    -0.06
    教程
    -0.06
    рной
    -0.05
    全程
    -0.05
    \|
    -0.05
     Europ
    -0.05
     International
    -0.05
    ciparum
    -0.05
    POSITIVE LOGITS
     recently
    0.07
     Archiv
    0.07
     최근
    0.07
     sejarah
    0.07
     recollections
    0.07
     تاريخ
    0.07
     ఇటీవల
    0.07
    現在
    0.07
     현재
    0.07
    回忆
    0.07
    Activations Density 0.003%

    No Known Activations