© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 118894
    Prev
    Next
    INDEX
    Explanations

    fuel injection systems

    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
     Recreational
    -0.07
    填
    -0.07
     filler
    -0.06
     recreational
    -0.06
    漂亮
    -0.06
     polyhedron
    -0.06
    还原
    -0.06
    对应的
    -0.06
     diversión
    -0.06
     Brochure
    -0.06
    POSITIVE LOGITS
     প্রযুক্ত
    0.06
    urgical
    0.06
     அமைந்துள்ளது
    0.05
     ошиб
    0.05
     stumble
    0.05
     verpflicht
    0.05
     itemscope
    0.05
     স্থাপিত
    0.05
     centralised
    0.05
     vault
    0.05
    Activations Density 0.011%

    No Known Activations