© 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. 129443
    Prev
    Next
    INDEX
    Explanations

    absorbent articles tampons

    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
     ギフト
    -0.06
    配送
    -0.06
     снаб
    -0.06
    包装
    -0.06
     promises
    -0.06
     durable
    -0.06
     tradeoffs
    -0.06
    宅配
    -0.06
    ue
    -0.05
     cared
    -0.05
    POSITIVE LOGITS
     trabajo
    0.07
    ⛏
    0.06
     vorhand
    0.06
     brake
    0.06
    现有
    0.06
     woodworking
    0.06
     machining
    0.06
     Brake
    0.06
     carpentry
    0.06
    こな
    0.06
    Activations Density 0.028%

    No Known Activations