© 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. 115964
    Prev
    Next
    INDEX
    Explanations

    units, disk, recorder, quotients, order

    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
    Negative Logits
    étant
    -0.08
    自己
    -0.08
    ັກ
    -0.07
     путем
    -0.06
    วัน
    -0.06
     devastated
    -0.06
     atât
    -0.06
    变得
    -0.06
    ேன்
    -0.06
     ধরনের
    -0.06
    POSITIVE LOGITS
     serta
    0.07
    =
    0.06
     demanded
    0.06
     undeniably
    0.06
    [!
    0.06
     tini
    0.06
     اقسام
    0.06
     unterschied
    0.06
    Quando
    0.06
    isNaN
    0.05
    Activations Density 0.004%

    No Known Activations