© 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. 117474
    Prev
    Next
    INDEX
    Explanations

    names of people and associated words

    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
     you
    -0.07
     ayudarte
    -0.06
     uncertainties
    -0.06
     více
    -0.06
     lebih
    -0.06
     youre
    -0.06
     অর্জন
    -0.06
     обеспечить
    -0.05
    pture
    -0.05
     lists
    -0.05
    POSITIVE LOGITS
    urah
    0.06
     такого
    0.06
     compar
    0.06
     situation
    0.06
     slob
    0.06
    ısının
    0.06
     جیسا
    0.06
    स्थिति
    0.05
    make
    0.05
    その後
    0.05
    Activations Density 0.002%

    No Known Activations