© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130705
    Prev
    Next
    INDEX
    Explanations

    research methods and data collection

    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
     Public
    -0.06
    出
    -0.06
     out
    -0.06
    Public
    -0.06
     outskirts
    -0.05
     dodge
    -0.05
    bl
    -0.05
    Bunch
    -0.05
     stderr
    -0.05
    ungg
    -0.05
    POSITIVE LOGITS
     ይታ
    0.07
     영국
    0.07
    제품
    0.07
     tục
    0.06
     siècle
    0.06
     खुले
    0.06
     इंग्लैंड
    0.06
     colony
    0.06
    相等
    0.06
     İng
    0.06
    Activations Density 0.161%

    No Known Activations