© 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. 118987
    Prev
    Next
    INDEX
    Explanations

    package peering

    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
    拍攝
    -0.07
     mentre
    -0.06
     grabación
    -0.06
     포인트
    -0.06
    误差
    -0.06
     grasped
    -0.06
     motion
    -0.06
    ትር
    -0.06
     mientras
    -0.06
     Precision
    -0.06
    POSITIVE LOGITS
     chatbots
    0.07
     partying
    0.06
     dialogues
    0.06
    исто
    0.06
     Viber
    0.06
    ☎
    0.06
    Chats
    0.06
     Sauna
    0.06
     Chats
    0.06
    popup
    0.06
    Activations Density 0.003%

    No Known Activations