© 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. 120566
    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
     that
    -0.06
     during
    -0.06
    conf
    -0.06
    事前に
    -0.06
    if
    -0.06
    :
    -0.06
     if
    -0.06
     suggests
    -0.06
    magic
    -0.06
    ML
    -0.05
    POSITIVE LOGITS
     cambia
    0.07
     appropriate
    0.07
    ponin
    0.06
    していますが
    0.06
     עם
    0.06
     verändert
    0.06
    就像
    0.06
     changé
    0.06
     с
    0.06
     cambiar
    0.06
    Activations Density 0.000%

    No Known Activations