© 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. 117686
    Prev
    Next
    INDEX
    Explanations

    Frank Luntz, famously

    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
    ❗
    -0.06
    同样
    -0.06
     জিনিস
    -0.06
    同樣
    -0.05
    orul
    -0.05
     hota
    -0.05
     रेस्ट
    -0.05
     flawless
    -0.05
     proposed
    -0.05
     peaceful
    -0.05
    POSITIVE LOGITS
    pseudo
    0.07
     pseudo
    0.07
     বৃত্তান্ত
    0.07
    trying
    0.06
     kogu
    0.06
     Eco
    0.06
     пределах
    0.06
     prób
    0.06
     alrededores
    0.06
     lever
    0.06
    Activations Density 0.023%

    No Known Activations