© 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. 117741
    Prev
    Next
    INDEX
    Explanations

    welcome and thank you phrases

    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
     everyone
    -0.07
     everybody
    -0.07
     όταν
    -0.07
    みんな
    -0.07
    োর্স
    -0.06
     skute
    -0.06
     সবাই
    -0.06
     실제
    -0.06
     tudi
    -0.06
     पनि
    -0.06
    POSITIVE LOGITS
    commons
    0.07
    对其
    0.06
    чиго
    0.06
     sundry
    0.06
    commonly
    0.06
     Contoh
    0.06
     handbook
    0.06
     licenses
    0.05
    cdnjs
    0.05
     किड्स
    0.05
    Activations Density 0.004%

    No Known Activations