© 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. 119561
    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
    但他
    -0.07
     জন্যও
    -0.06
    现在的
    -0.06
     بہانہ
    -0.06
    But
    -0.06
     chứ
    -0.06
     mutta
    -0.06
     keepsake
    -0.05
    consulté
    -0.05
     konsult
    -0.05
    POSITIVE LOGITS
    ่วน
    0.07
     последнего
    0.06
     গত
    0.06
     শ্রে
    0.06
     последнее
    0.06
     estremamente
    0.06
     markedly
    0.06
     послед
    0.06
     posled
    0.06
     swiftly
    0.06
    Activations Density 0.000%

    No Known Activations