© 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. 129764
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions with operators

    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
     обоих
    -0.06
     sementara
    -0.06
     Microbiol
    -0.06
     অ্য
    -0.06
     contratar
    -0.06
    нях
    -0.06
     местного
    -0.06
     problemas
    -0.06
    られます
    -0.06
     pubescent
    -0.06
    POSITIVE LOGITS
     used
    0.06
    松
    0.06
    应用于
    0.06
    运用
    0.06
     bepa
    0.06
     utilizamos
    0.06
     określ
    0.06
    ↵
    0.06
    value
    0.06
     relied
    0.06
    Activations Density 0.016%

    No Known Activations