© 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. 120465
    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
     an
    -0.07
     a
    -0.06
     the
    -0.06
     sprawy
    -0.05
    ore
    -0.05
    inski
    -0.05
    Կ
    -0.05
    系統
    -0.05
    ଭ
    -0.05
     অবরোধ
    -0.05
    POSITIVE LOGITS
    🏚
    0.08
     quase
    0.07
     двой
    0.07
    🌇
    0.07
    🚱
    0.07
     hampir
    0.07
     criando
    0.07
     casi
    0.07
    🕓
    0.06
    🥥
    0.06
    Activations Density 0.000%

    No Known Activations