© 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. 128815
    Prev
    Next
    INDEX
    Explanations

    census population

    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
     atualmente
    -0.07
    名字
    -0.07
     attualmente
    -0.06
    phony
    -0.06
     operates
    -0.06
     fosters
    -0.06
    people
    -0.06
     বাংলাদেশের
    -0.06
     currently
    -0.06
     allows
    -0.06
    POSITIVE LOGITS
     pilihan
    0.06
     keuze
    0.06
    也可
    0.06
     jauh
    0.06
    selectAll
    0.06
    这里
    0.05
    жди
    0.05
    的选择
    0.05
     قبل
    0.05
     mulig
    0.05
    Activations Density 0.004%

    No Known Activations