© 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
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130113
    Prev
    Next
    INDEX
    Explanations

    social media platforms

    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
     যা
    -0.07
     которое
    -0.06
     Snapdragon
    -0.06
     Servicios
    -0.06
    ユーザー
    -0.06
    Organic
    -0.05
    service
    -0.05
    openai
    -0.05
    сная
    -0.05
     follic
    -0.05
    POSITIVE LOGITS
     tradi
    0.07
     тради
    0.06
    λης
    0.06
     traditionnel
    0.06
     އި
    0.06
     tradicionales
    0.06
     डेयरी
    0.06
     mailing
    0.06
    traditional
    0.06
     depends
    0.06
    Activations Density 0.008%

    No Known Activations