© 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. 116964
    Prev
    Next
    INDEX
    Explanations

    Features

    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
     কাছ
    -0.06
     వాటి
    -0.06
    hu
    -0.06
     கடைசி
    -0.06
     अब
    -0.06
     supply
    -0.06
    verson
    -0.05
    ...');
    -0.05
     resounding
    -0.05
     dung
    -0.05
    POSITIVE LOGITS
     while
    0.07
     WHILE
    0.06
     উৎপ
    0.06
     svjets
    0.06
    while
    0.06
     mientras
    0.06
     While
    0.06
    而出
    0.06
    を使用して
    0.06
     internasional
    0.06
    Activations Density 0.009%

    No Known Activations