© 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. 129510
    Prev
    Next
    INDEX
    Explanations

    review and verification

    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
    准备
    -0.08
    準備
    -0.07
    实现
    -0.07
    制定
    -0.07
     준비
    -0.06
     přip
    -0.06
     തയ്യാ
    -0.06
     preparations
    -0.06
    preparation
    -0.06
     preparation
    -0.06
    POSITIVE LOGITS
     verifica
    0.06
     صحت
    0.06
    かで
    0.06
     (!
    0.06
     review
    0.06
     check
    0.05
    ئين
    0.05
     ){
    0.05
     validating
    0.05
     otherworldly
    0.05
    Activations Density 0.001%

    No Known Activations