© 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. 117787
    Prev
    Next
    INDEX
    Explanations

    dates, years, and months

    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
    Through
    -0.08
    ເນ
    -0.07
     Through
    -0.06
     dingen
    -0.06
     przedmiot
    -0.06
     ellas
    -0.06
    idas
    -0.06
    ,[
    -0.06
    through
    -0.06
    诠
    -0.05
    POSITIVE LOGITS
     uved
    0.06
     keep
    0.06
     ketika
    0.06
    改变
    0.06
     Ketika
    0.06
    變化
    0.06
    改變
    0.06
    ങ്ങളും
    0.06
     infrequent
    0.06
     לא
    0.06
    Activations Density 0.002%

    No Known Activations