© 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. 130732
    Prev
    Next
    INDEX
    Explanations

    record labels and media companies

    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
    羰
    -0.06
    ually
    -0.06
     selection
    -0.06
     start
    -0.06
     receiving
    -0.06
    ucine
    -0.06
    beyond
    -0.06
     नॉट
    -0.05
    START
    -0.05
     sharks
    -0.05
    POSITIVE LOGITS
     如
    0.06
     darf
    0.06
     lavori
    0.06
     dari
    0.05
     μαζί
    0.05
    所有的
    0.05
     refreshments
    0.05
    如
    0.05
     razem
    0.05
     南
    0.05
    Activations Density 0.015%

    No Known Activations