© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130420
    Prev
    Next
    INDEX
    Explanations

    `#include <`

    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
    Continue
    -0.06
    ครั้ง
    -0.06
     my
    -0.06
     Thur
    -0.06
    واصل
    -0.06
     retos
    -0.06
     продолжаем
    -0.06
     نظام
    -0.06
     continuare
    -0.06
     summa
    -0.06
    POSITIVE LOGITS
     mesma
    0.07
    exactly
    0.06
     गावा
    0.06
    Exactly
    0.06
     دقی
    0.06
    Depending
    0.06
     exactly
    0.06
     assurances
    0.06
    ieft
    0.05
    稍
    0.05
    Activations Density 0.011%

    No Known Activations