© 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. 116171
    Prev
    Next
    INDEX
    Explanations

    wanting to do

    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
     które
    -0.07
    战斗
    -0.07
     zoo
    -0.07
     aprox
    -0.07
     sudah
    -0.07
     cuando
    -0.06
     quando
    -0.06
     wechseln
    -0.06
     entire
    -0.06
     меня
    -0.06
    POSITIVE LOGITS
    писать
    0.06
    legung
    0.06
    ucer
    0.06
    賀
    0.06
    Means
    0.06
     ответствен
    0.06
    means
    0.06
     mengucapkan
    0.05
    хал
    0.05
     multifunction
    0.05
    Activations Density 0.013%

    No Known Activations