© 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
    2. Gemma-4-31B
    3. 30-RES-MATRYOSHKA-131K
    4. 118472
    Prev
    Next
    INDEX
    Explanations

    stores and friends

    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
     during
    -0.06
     خلال
    -0.06
     jorn
    -0.06
     nên
    -0.06
     tijdens
    -0.05
     सुमारे
    -0.05
     পৃথক
    -0.05
     señ
    -0.05
     childlike
    -0.05
     uranium
    -0.05
    POSITIVE LOGITS
    Lost
    0.06
    حياته
    0.06
    送料無料
    0.06
    летка
    0.06
     ग्वालियर
    0.06
     उसे
    0.06
    nda
    0.06
     είχε
    0.05
     Solutions
    0.05
     prins
    0.05
    Activations Density 0.001%

    No Known Activations