© 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. 130311
    Prev
    Next
    INDEX
    Explanations

    numbers and quantities

    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
     если
    -0.06
     होणार
    -0.06
    決して
    -0.06
     trotz
    -0.06
     भले
    -0.06
    လား
    -0.05
    если
    -0.05
    Anti
    -0.05
     nonostante
    -0.05
    ：
    -0.05
    POSITIVE LOGITS
     that
    0.07
     तकरीबन
    0.06
     as
    0.06
     two
    0.06
     یک
    0.06
    いくつか
    0.06
     কয়েকটি
    0.06
    几个
    0.06
     zwei
    0.06
     två
    0.06
    Activations Density 0.001%

    No Known Activations