© 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. 116993
    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
    ありが
    -0.06
     enduring
    -0.06
    licer
    -0.06
    connections
    -0.06
     ưa
    -0.06
     forbind
    -0.06
     отлично
    -0.06
    april
    -0.06
     зака
    -0.05
     perfe
    -0.05
    POSITIVE LOGITS
     पिछले
    0.06
    มัน
    0.06
    டர்
    0.06
     विशेषज्ञों
    0.06
     exist
    0.06
     domác
    0.06
     व्हाट्स
    0.06
     یک
    0.06
    いわ
    0.06
     actos
    0.06
    Activations Density 0.000%

    No Known Activations