© 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. 120876
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    َيْ
    -0.06
    é
    -0.06
     rigidity
    -0.06
     resemblance
    -0.06
     preempt
    -0.06
     similarity
    -0.06
     discernment
    -0.06
    elerin
    -0.05
     হলেও
    -0.05
     Однако
    -0.05
    POSITIVE LOGITS
     find
    0.07
    find
    0.07
    あらゆる
    0.07
     finds
    0.07
     continuamente
    0.06
     continually
    0.06
     conte
    0.06
    それが
    0.06
     finden
    0.06
     любых
    0.06
    Activations Density 0.000%

    No Known Activations