© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129884
    Prev
    Next
    INDEX
    Explanations

    Torah, Moses, Ten Commandments

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     அனுமதி
    -0.06
     completion
    -0.06
    enched
    -0.06
    completed
    -0.06
    ???
    -0.06
    完
    -0.06
     completions
    -0.06
     Gate
    -0.05
     Completed
    -0.05
     until
    -0.05
    POSITIVE LOGITS
     Zoning
    0.07
     grouping
    0.06
     zoning
    0.06
    RET
    0.06
    űt
    0.06
    ussion
    0.06
     Authentication
    0.06
     scheduler
    0.06
    ettes
    0.06
     konten
    0.06
    Activations Density 0.003%

    No Known Activations