© 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. 117538
    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
    诱
    -0.06
     hinting
    -0.06
     пры
    -0.06
     jumping
    -0.06
     hinted
    -0.06
     jumped
    -0.06
     fond
    -0.06
     Jumping
    -0.06
     المنتخب
    -0.06
    考試
    -0.06
    POSITIVE LOGITS
     повседнев
    0.07
    柴
    0.07
    Contrib
    0.06
     layering
    0.06
    োলন
    0.06
     積
    0.06
    TAR
    0.06
    èdes
    0.06
    텐
    0.06
    積み
    0.06
    Activations Density 0.000%

    No Known Activations