© 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. 128944
    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
     fears
    -0.06
     இன்றைய
    -0.06
     оконча
    -0.06
     starten
    -0.06
     implode
    -0.05
    плю
    -0.05
    💕
    -0.05
     መጨ
    -0.05
     overjoyed
    -0.05
     понятия
    -0.05
    POSITIVE LOGITS
     différent
    0.07
     ওয়
    0.06
    のお
    0.06
     forb
    0.06
     এইভাবে
    0.06
    に
    0.06
    這個
    0.06
     different
    0.06
     ingredient
    0.06
     differentiate
    0.06
    Activations Density 0.003%

    No Known Activations