© 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. 117229
    Prev
    Next
    INDEX
    Explanations

    Stim+ulation, Dis+ordered, Since+ the

    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
     other
    -0.08
     на
    -0.07
     다른
    -0.07
     andere
    -0.07
     had
    -0.06
    其他
    -0.06
     to
    -0.06
     বণ্ট
    -0.06
    注意事项
    -0.06
     på
    -0.06
    POSITIVE LOGITS
     જેટ
    0.07
     responsiveness
    0.06
    Even
    0.06
     నాకు
    0.06
     nyní
    0.06
    Chair
    0.06
    Its
    0.06
    летнего
    0.06
    しまう
    0.06
    今の
    0.06
    Activations Density 0.004%

    No Known Activations