© 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. 116228
    Prev
    Next
    INDEX
    Explanations

    publishing, publishers, company, industry

    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
    策略
    -0.07
     Too
    -0.06
     too
    -0.06
     for
    -0.06
    циона
    -0.06
     California
    -0.06
    too
    -0.06
    䒴
    -0.05
     :(
    -0.05
     music
    -0.05
    POSITIVE LOGITS
    दैन
    0.06
     PCBs
    0.06
    人体
    0.06
     lunatic
    0.06
    LIMITED
    0.06
     consect
    0.06
    煒
    0.06
     Sare
    0.06
     കമ്മി
    0.06
     взаимодействия
    0.06
    Activations Density 0.007%

    No Known Activations