© 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. 130038
    Prev
    Next
    INDEX
    Explanations

    data deletion or consumption

    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
    ابقة
    -0.06
     utilizamos
    -0.06
     cujo
    -0.06
     cuyo
    -0.06
    satisfied
    -0.06
    Unser
    -0.06
    Edit
    -0.06
    abal
    -0.06
     curvature
    -0.06
    ขั้นตอน
    -0.06
    POSITIVE LOGITS
     vì
    0.06
     самых
    0.06
    vì
    0.06
     쌓
    0.06
    accumulation
    0.06
     accumulating
    0.06
     accumulation
    0.06
     mencapai
    0.05
     voluminous
    0.05
    ড়ে
    0.05
    Activations Density 0.085%

    No Known Activations