© 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. 119760
    Prev
    Next
    INDEX
    Explanations

    box office and gross revenue

    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
     prev
    -0.07
     />,
    -0.07
     military
    -0.07
     بتكون
    -0.07
     반드시
    -0.07
    还得
    -0.07
     uitgevoerd
    -0.07
     FIVE
    -0.06
     ఇతర
    -0.06
     recre
    -0.06
    POSITIVE LOGITS
    midd
    0.06
     project
    0.06
     жал
    0.05
     only
    0.05
    我
    0.05
    ཇ
    0.05
    ribute
    0.05
     linkages
    0.05
     statusBar
    0.05
     مساعد
    0.05
    Activations Density 0.002%

    No Known Activations