© 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. 129753
    Prev
    Next
    INDEX
    Explanations

    polyamines, Q: overload, Howard Schultz, Tag Challenge

    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
     مثل
    -0.08
     یکی
    -0.07
    Parliament
    -0.07
     sorrow
    -0.06
     অনেক
    -0.06
     οργαν
    -0.06
    :
    -0.06
    ようです
    -0.06
     پہلی
    -0.06
    
    -0.06
    POSITIVE LOGITS
     for
    0.08
     für
    0.06
     kleiner
    0.06
    हमारी
    0.06
     для
    0.05
     For
    0.05
     ताजा
    0.05
     फॉर
    0.05
    स्टूड
    0.05
    for
    0.05
    Activations Density 0.001%

    No Known Activations