© 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. 116953
    Prev
    Next
    INDEX
    Explanations

    children need, achieve by, anti-poverty tool

    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
     ridiculously
    -0.07
     apparent
    -0.06
     evident
    -0.06
     иначе
    -0.06
     official
    -0.06
    ंकित
    -0.06
     important
    -0.06
     Typical
    -0.06
     nonchal
    -0.06
     typical
    -0.06
    POSITIVE LOGITS
     to
    0.06
     всех
    0.06
     갔다
    0.06
     و
    0.06
    齐
    0.06
     Actually
    0.06
     людей
    0.06
     उच्च
    0.06
     दिखाना
    0.06
     будут
    0.06
    Activations Density 0.029%

    No Known Activations