© 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. 129594
    Prev
    Next
    INDEX
    Explanations

    numbers and words

    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
     purported
    -0.06
     jejich
    -0.06
     मासूम
    -0.06
     komponen
    -0.06
    겠
    -0.06
     prawdopod
    -0.06
    лую
    -0.06
     כך
    -0.06
     Они
    -0.06
    ijų
    -0.06
    POSITIVE LOGITS
     three
    0.07
    我们
    0.07
     four
    0.06
     economists
    0.06
     nosso
    0.06
     বিশ্রাম
    0.06
     two
    0.06
     troca
    0.06
     হোয়াটসঅ্যাপ
    0.06
     we
    0.06
    Activations Density 0.003%

    No Known Activations