© 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. 129595
    Prev
    Next
    INDEX
    Explanations

    video web

    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
     사는
    -0.06
     عند
    -0.06
    新建
    -0.06
    றவு
    -0.06
     две
    -0.06
    Support
    -0.06
     definito
    -0.06
     되는
    -0.06
     rowing
    -0.06
     gripped
    -0.05
    POSITIVE LOGITS
     これ
    0.07
     lại
    0.06
     现在
    0.06
     这
    0.06
     これは
    0.06
    everything
    0.06
     хотя
    0.06
    now
    0.06
     也
    0.06
     Although
    0.05
    Activations Density 0.060%

    No Known Activations