© 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. 117078
    Prev
    Next
    INDEX
    Explanations

    relationship expert

    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
     உறுப்பினர்
    -0.06
     grueling
    -0.06
    见面
    -0.06
     ceremony
    -0.06
     immediacy
    -0.06
     continual
    -0.06
    чности
    -0.06
     dijadikan
    -0.06
     inviol
    -0.06
     width
    -0.06
    POSITIVE LOGITS
     ใด
    0.06
     gây
    0.06
    fired
    0.06
    はどう
    0.06
    輸出
    0.05
     сообщает
    0.05
    arently
    0.05
    ziale
    0.05
     naturally
    0.05
     criticised
    0.05
    Activations Density 0.018%

    No Known Activations