© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 120693
    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
     பழைய
    -0.07
     Некоторые
    -0.07
     Quando
    -0.07
     Несмотря
    -0.06
     some
    -0.06
    橼
    -0.06
     trotz
    -0.06
     Когда
    -0.06
     dönt
    -0.06
     an
    -0.06
    POSITIVE LOGITS
    contribution
    0.06
     காலம்
    0.05
    unpublished
    0.05
     服
    0.05
     contribution
    0.05
    ctuations
    0.05
    Re
    0.05
     kadın
    0.05
          
    0.05
    We
    0.05
    Activations Density 0.000%

    No Known Activations