© 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. 117281
    Prev
    Next
    INDEX
    Explanations

    graph Associated

    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
    やお
    -0.06
     Tribunal
    -0.06
     ۱۳
    -0.06
     müşteri
    -0.06
         
    -0.06
     delectable
    -0.06
     تصمیم
    -0.06
     berken
    -0.06
    ಲಾ
    -0.06
     clums
    -0.06
    POSITIVE LOGITS
     पदाधिकारियों
    0.06
    innerText
    0.06
    鸹
    0.06
    收
    0.06
     ఎలా
    0.06
     enkele
    0.06
    如何
    0.06
    ็บ
    0.06
     how
    0.06
    怎么样
    0.06
    Activations Density 0.002%

    No Known Activations