© 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. 120434
    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
    ほとんど
    -0.07
    öll
    -0.06
     appearing
    -0.06
     বেশিরভাগ
    -0.06
     preparation
    -0.06
    ъек
    -0.06
     vorbere
    -0.06
     freight
    -0.06
    几乎
    -0.06
     prépar
    -0.06
    POSITIVE LOGITS
    の使用
    0.06
     sharing
    0.06
     क्रॉस
    0.06
     incompatibility
    0.06
     उपयोग
    0.06
     Management
    0.06
     manag
    0.06
     incompat
    0.06
     management
    0.06
     dangers
    0.06
    Activations Density 0.000%

    No Known Activations