© 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. 129404
    Prev
    Next
    INDEX
    Explanations

    chemical design

    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
     authent
    -0.07
     intentar
    -0.06
     кілька
    -0.06
    旧
    -0.06
     estuvo
    -0.06
     लखनऊ
    -0.06
    subTest
    -0.06
     spielen
    -0.06
    舊
    -0.06
     Purchased
    -0.06
    POSITIVE LOGITS
     design
    0.09
    设计
    0.08
     designs
    0.08
     طراحی
    0.07
     Design
    0.07
    design
    0.07
     डिजाइन
    0.07
    designs
    0.07
    設計
    0.07
    Design
    0.06
    Activations Density 0.044%

    No Known Activations