© 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. 117498
    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
     Reihe
    -0.07
     Simpl
    -0.07
    recieve
    -0.06
     ____________
    -0.06
     profond
    -0.06
    ವುದ
    -0.06
     violet
    -0.06
     quisiera
    -0.06
     chrys
    -0.06
     recieve
    -0.06
    POSITIVE LOGITS
     evaluator
    0.06
    orama
    0.06
     appena
    0.06
     नजदी
    0.06
     synchronization
    0.06
     кілька
    0.06
     jeszcze
    0.06
    eware
    0.06
     dichos
    0.06
    usan
    0.05
    Activations Density 0.000%

    No Known Activations