© 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. 117518
    Prev
    Next
    INDEX
    Explanations

    multicarrier mobile communication system

    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
    ratings
    -0.07
     Celebrate
    -0.06
     vie
    -0.06
     intens
    -0.06
    uasion
    -0.06
    engineered
    -0.06
     leng
    -0.06
     endure
    -0.06
    चेता
    -0.06
     nàng
    -0.06
    POSITIVE LOGITS
    を採用
    0.07
     broad
    0.06
     systeem
    0.06
     அடிப்படையில்
    0.06
     breadth
    0.06
     adopted
    0.06
     내부
    0.06
     concept
    0.06
     הרב
    0.06
    蝟
    0.06
    Activations Density 0.009%

    No Known Activations