© 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. 116061
    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
    andal
    -0.06
     थे
    -0.06
     or
    -0.06
     ought
    -0.06
     burgl
    -0.06
    िवा
    -0.06
    exerc
    -0.05
    ويض
    -0.05
    といった
    -0.05
     bør
    -0.05
    POSITIVE LOGITS
     আমেরিকা
    0.07
     আজকাল
    0.06
     في
    0.06
     migliorare
    0.06
    mettre
    0.06
    걔
    0.06
     चुनने
    0.06
     refine
    0.06
     streamline
    0.06
     Ladder
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.