© 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. 119323
    Prev
    Next
    INDEX
    Explanations

    numbers before or after a number

    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
     through
    -0.06
    dude
    -0.06
     resalt
    -0.06
    他
    -0.06
     হত্যাকাণ্ড
    -0.06
     remove
    -0.06
     لحاظ
    -0.06
     første
    -0.06
     durch
    -0.06
     into
    -0.06
    POSITIVE LOGITS
     какой
    0.07
     spécialement
    0.06
     какая
    0.06
     تاز
    0.06
     nový
    0.06
     cabang
    0.06
     nějak
    0.06
     هذه
    0.06
     merry
    0.06
    ompok
    0.06
    Activations Density 0.015%

    No Known Activations