© 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. 118262
    Prev
    Next
    INDEX
    Explanations

    Q: followed by colon

    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
     قیمت
    -0.06
     assisting
    -0.06
     Foreign
    -0.06
     grinning
    -0.06
     getting
    -0.06
     onde
    -0.06
     goofy
    -0.06
     where
    -0.06
     prezzo
    -0.06
     cynical
    -0.06
    POSITIVE LOGITS
     Sicilia
    0.07
    研究
    0.06
    studied
    0.06
     Skyrim
    0.06
    の研究
    0.06
    実験
    0.06
     thermodynamics
    0.06
     அழை
    0.06
     experimental
    0.06
     testes
    0.06
    Activations Density 0.002%

    No Known Activations