© 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. 129758
    Prev
    Next
    INDEX
    Explanations

    words ending in 'ty'

    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
    ,!
    -0.06
    воро
    -0.06
    लियों
    -0.06
    HEIGHT
    -0.06
     cooperation
    -0.06
     Lua
    -0.06
    utebol
    -0.06
     Anakin
    -0.06
    pped
    -0.06
     Olympic
    -0.06
    POSITIVE LOGITS
     महाराष्ट्रा
    0.08
     rar
    0.07
    資格
    0.07
     different
    0.07
     მხოლოდ
    0.06
     verschillende
    0.06
     farklı
    0.06
    HING
    0.06
     사이즈
    0.06
     স্বামীকে
    0.05
    Activations Density 0.020%

    No Known Activations