© 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. 117548
    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
     
    -0.07
    (
    -0.06
    えています
    -0.06
    Context
    -0.05
    iver
    -0.05
    になっています
    -0.05
     had
    -0.05
    =
    -0.05
     продолжи
    -0.05
     وس
    -0.05
    POSITIVE LOGITS
     egyik
    0.07
     keel
    0.06
    திரு
    0.06
     அவரு
    0.06
     ক্ষতি
    0.06
    ρών
    0.06
     அவரின்
    0.06
     পিছ
    0.06
    THERE
    0.06
     daí
    0.06
    Activations Density 0.000%

    No Known Activations