© 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. 128470
    Prev
    Next
    INDEX
    Explanations

    broadcasts, songs, detection, websites

    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
     definition
    -0.07
     packing
    -0.06
     mág
    -0.06
    IMPLEMENT
    -0.06
     sometimes
    -0.06
     Packing
    -0.06
    神奇
    -0.06
     международ
    -0.06
     postgres
    -0.06
     PostgreSQL
    -0.06
    POSITIVE LOGITS
     bajo
    0.06
    구성
    0.06
    loads
    0.06
    우리
    0.06
     बनाएं
    0.06
     séance
    0.05
     contraire
    0.05
     sejumlah
    0.05
    किला
    0.05
     broadcast
    0.05
    Activations Density 0.003%

    No Known Activations