© 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. 118723
    Prev
    Next
    INDEX
    Explanations

    through digital downloading or streaming

    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
    不太
    -0.07
     wanneer
    -0.06
     पदार्
    -0.06
     pretty
    -0.06
    你是
    -0.06
    刚刚
    -0.06
    भेद
    -0.06
    这是
    -0.06
     amendment
    -0.06
     vapor
    -0.06
    POSITIVE LOGITS
     základ
    0.06
     الأساس
    0.06
     keuze
    0.06
    izantes
    0.06
     началом
    0.06
     bases
    0.06
    änä
    0.06
     спеціа
    0.05
     மக்களுக்கு
    0.05
     stated
    0.05
    Activations Density 0.010%

    No Known Activations