© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120901
    Prev
    Next
    INDEX
    Explanations

    only

    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
    Negative Logits
     друзья
    -0.06
     hostility
    -0.06
     выпусти
    -0.06
     reac
    -0.06
     impec
    -0.06
    Values
    -0.06
     gồm
    -0.06
    DEF
    -0.06
     সৈন্য
    -0.06
     नौकर
    -0.05
    POSITIVE LOGITS
     sadece
    0.08
     فقط
    0.07
     csak
    0.07
     only
    0.07
     лишь
    0.07
     jedynie
    0.07
     chỉ
    0.07
     მხოლოდ
    0.07
     tylko
    0.06
    如何在
    0.06
    Activations Density 0.005%

    No Known Activations