© 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. 120251
    Prev
    Next
    INDEX
    Explanations

    performance, throughput, transfer

    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
     секунд
    -0.07
    稍微
    -0.07
     hoje
    -0.07
    searching
    -0.07
    Searching
    -0.07
     poucos
    -0.06
     estimado
    -0.06
     Searching
    -0.06
     few
    -0.06
     unnecessary
    -0.06
    POSITIVE LOGITS
     conventions
    0.06
    成果
    0.06
     வெற்ற
    0.06
     বিবাহ
    0.06
     isolate
    0.06
     limitations
    0.06
     institute
    0.06
    hasilan
    0.06
     eredmény
    0.06
     output
    0.06
    Activations Density 0.007%

    No Known Activations