© 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. 119173
    Prev
    Next
    INDEX
    Explanations

    health problems

    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
     bardzo
    -0.08
     очень
    -0.07
     vrlo
    -0.07
     très
    -0.07
    大き
    -0.07
    
    -0.07
     very
    -0.07
     excepting
    -0.06
     така
    -0.06
    輸出
    -0.06
    POSITIVE LOGITS
     miraculous
    0.06
     আবারও
    0.06
    4
    0.06
     information
    0.05
     通过
    0.05
     eradication
    0.05
    3
    0.05
     otherworldly
    0.05
    informed
    0.05
     accurately
    0.05
    Activations Density 0.039%

    No Known Activations