© 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. 130570
    Prev
    Next
    INDEX
    Explanations

    programming constructs and types

    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
     রক
    -0.07
     दिसत
    -0.06
     sekaligus
    -0.06
     alcuni
    -0.06
    stanford
    -0.06
     related
    -0.06
    ´
    -0.06
     partic
    -0.05
     valuable
    -0.05
     active
    -0.05
    POSITIVE LOGITS
     نوشته
    0.07
     পারে
    0.07
    essentially
    0.06
    prettier
    0.06
    Yield
    0.06
     possono
    0.06
    另一个
    0.06
    哏
    0.06
     tulis
    0.06
     urna
    0.06
    Activations Density 0.005%

    No Known Activations