© 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. 130646
    Prev
    Next
    INDEX
    Explanations

    non-English characters or foreign words

    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
     fanden
    -0.06
     subjects
    -0.06
     ஆரம்பித்த
    -0.06
     بأن
    -0.06
    ե
    -0.05
     그래서
    -0.05
    ,”
    -0.05
     headquarters
    -0.05
     one
    -0.05
     enthusiasm
    -0.05
    POSITIVE LOGITS
    禁止
    0.06
     മഹാ
    0.06
     храни
    0.06
    から
    0.06
     പിന്തുണ
    0.06
     করতে
    0.06
     रिव्यू
    0.06
     असल्यास
    0.06
    LiveData
    0.06
    ඬ
    0.06
    Activations Density 0.004%

    No Known Activations