© 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. 128198
    Prev
    Next
    INDEX
    Explanations

    code documentation and markup

    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
     которые
    -0.07
     где
    -0.07
     które
    -0.07
     which
    -0.06
     которую
    -0.06
     aumentar
    -0.06
     மக்களின்
    -0.06
    ซึ่ง
    -0.06
    Gson
    -0.06
     које
    -0.06
    POSITIVE LOGITS
     należy
    0.06
    ცა
    0.05
    empio
    0.05
    लेक्ट्र
    0.05
    swedish
    0.05
    va
    0.05
    orch
    0.05
     raies
    0.05
     Perr
    0.05
     mời
    0.05
    Activations Density 0.001%

    No Known Activations