© 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. 119420
    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
    但这
    -0.06
     idk
    -0.06
     (
    -0.06
    该
    -0.05
     amat
    -0.05
     cosas
    -0.05
    MATERIAL
    -0.05
     этой
    -0.05
     erreurs
    -0.05
     எழுது
    -0.05
    POSITIVE LOGITS
     negotiations
    0.06
     quand
    0.06
    akkam
    0.06
    とか
    0.06
    妄
    0.06
    综合
    0.06
     بھائی
    0.06
     new
    0.06
     unsightly
    0.06
     veya
    0.06
    Activations Density 0.000%

    No Known Activations