© 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. 116315
    Prev
    Next
    INDEX
    Explanations

    set intersection and restriction

    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
     প্রতার
    -0.06
    完成
    -0.06
     successfully
    -0.06
     their
    -0.06
    agno
    -0.05
    Gap
    -0.05
    rror
    -0.05
     little
    -0.05
     সেক্ট
    -0.05
    pectral
    -0.05
    POSITIVE LOGITS
     jamais
    0.06
     त्योहार
    0.06
    ซึ่ง
    0.06
    すると
    0.06
     नए
    0.06
    이라
    0.06
    하면
    0.06
     meist
    0.06
     високо
    0.06
     شدید
    0.06
    Activations Density 0.002%

    No Known Activations