© 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. 119161
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     dazu
    -0.06
    戻
    -0.06
    shortest
    -0.06
    こういう
    -0.05
    요
    -0.05
     yourselves
    -0.05
    ՞
    -0.05
    那个
    -0.05
     আপডেট
    -0.05
    に戻
    -0.05
    POSITIVE LOGITS
     house
    0.08
     في
    0.07
     στην
    0.06
     through
    0.06
     வழியாக
    0.06
     při
    0.06
     असल्याने
    0.06
     undersea
    0.06
     अधिकांश
    0.06
    Ｆ
    0.06
    Activations Density 0.000%

    No Known Activations