© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120494
    Prev
    Next
    INDEX
    Explanations

    -ization, -ization, -ification, -ize

    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
    新たな
    -0.07
    而出
    -0.06
     દે
    -0.06
     ขณะ
    -0.06
     targeted
    -0.06
     transparency
    -0.06
    Specifically
    -0.06
     informacji
    -0.06
     información
    -0.06
     새로운
    -0.06
    POSITIVE LOGITS
     just
    0.07
     you
    0.06
     quinto
    0.06
     juste
    0.06
     معادله
    0.06
     negoci
    0.06
     வரலா
    0.05
     teeth
    0.05
    ivers
    0.05
     rhum
    0.05
    Activations Density 0.028%

    No Known Activations