© 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. 116128
    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
    Not in Any Lists

    No Comments

    Negative Logits
    সহ
    -0.06
     apellidos
    -0.06
    자를
    -0.06
    itl
    -0.06
     Mujer
    -0.06
     danno
    -0.06
     सहयोग
    -0.06
    वंत
    -0.05
     Zwei
    -0.05
    确实
    -0.05
    POSITIVE LOGITS
     with
    0.07
     if
    0.07
     넘
    0.07
     While
    0.06
     With
    0.06
    novel
    0.06
     high
    0.06
     좋아하는
    0.06
     They
    0.06
     ethn
    0.06
    Activations Density 0.000%

    No Known Activations