© 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. 128301
    Prev
    Next
    INDEX
    Explanations

    selection, background

    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
    參與
    -0.06
    孵
    -0.06
     ஆரம்ப
    -0.06
     শুরুতে
    -0.06
     отношений
    -0.06
    参与
    -0.06
     opgenomen
    -0.06
    基本的な
    -0.06
     व्यवस्था
    -0.05
     참여
    -0.05
    POSITIVE LOGITS
     selecting
    0.07
     배경
    0.07
     selects
    0.07
     sélection
    0.06
     selection
    0.06
     selección
    0.06
     selections
    0.06
    风景
    0.06
    背景
    0.06
     wallpaper
    0.06
    Activations Density 0.007%

    No Known Activations