© 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. 127982
    Prev
    Next
    INDEX
    Explanations

    GO, coli, black tea

    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
     because
    -0.08
     conventional
    -0.07
     fordi
    -0.07
     çünkü
    -0.06
     karena
    -0.06
     لأن
    -0.06
     classical
    -0.06
     porque
    -0.06
     omdat
    -0.06
    ScriptInterface
    -0.06
    POSITIVE LOGITS
     aproximadamente
    0.07
     Flores
    0.06
    address
    0.06
     Understanding
    0.06
    大约
    0.06
     eet
    0.06
     Ў
    0.06
     материа
    0.06
     ignorant
    0.06
    っぱい
    0.06
    Activations Density 0.013%

    No Known Activations