© 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. 129888
    Prev
    Next
    INDEX
    Explanations

    programming keywords and identifiers

    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
     pues
    -0.07
    กรณ์
    -0.07
    主な
    -0.06
     جدید
    -0.06
    记得
    -0.06
    성에
    -0.06
     आपले
    -0.05
    ใหม่
    -0.05
    으니
    -0.05
     incessant
    -0.05
    POSITIVE LOGITS
     любого
    0.07
    封闭
    0.06
     elef
    0.06
     ৯ম
    0.06
    ẞ
    0.06
    supabase
    0.06
     alerted
    0.06
     uzav
    0.05
     لري
    0.05
     করেও
    0.05
    Activations Density 0.001%

    No Known Activations