© 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. 119011
    Prev
    Next
    INDEX
    Explanations

    questions about second/closest values

    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
     различни
    -0.07
     different
    -0.07
     différentes
    -0.07
     다른
    -0.06
     különböző
    -0.06
     verschiedene
    -0.06
     다양한
    -0.06
    :
    -0.06
     other
    -0.06
     различными
    -0.06
    POSITIVE LOGITS
     begg
    0.06
    first
    0.06
     Pertama
    0.06
     ముందు
    0.06
     first
    0.06
    资讯
    0.06
     before
    0.06
    ные
    0.06
     antes
    0.06
     criando
    0.06
    Activations Density 0.002%

    No Known Activations