© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 129219
    Prev
    Next
    INDEX
    Explanations

    HTML structure tags

    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
     जरूरी
    -0.07
    本身的
    -0.07
    应用的
    -0.07
     defy
    -0.07
     dangers
    -0.06
     calmer
    -0.06
    必要的
    -0.06
     with
    -0.06
     يجب
    -0.06
    อื่นๆ
    -0.06
    POSITIVE LOGITS
    同じ
    0.07
     artística
    0.06
    killed
    0.06
     kuvvet
    0.06
     toàn
    0.06
     künstler
    0.06
    チョコレート
    0.06
    点了点头
    0.06
    ということは
    0.06
     расположение
    0.06
    Activations Density 0.001%

    No Known Activations