© 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. 118830
    Prev
    Next
    INDEX
    Explanations

    discharge, arrester, electricity

    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
    甠
    -0.07
     continuous
    -0.07
     continuously
    -0.06
     Corfu
    -0.06
     folyam
    -0.06
     femininity
    -0.06
     lebens
    -0.06
     радио
    -0.06
    continuous
    -0.06
     ITV
    -0.06
    POSITIVE LOGITS
     różnych
    0.07
     разных
    0.06
    感兴趣
    0.06
    几种
    0.06
     triggering
    0.06
     різних
    0.06
    ↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵↵
    0.06
     між
    0.06
     showroom
    0.06
     different
    0.06
    Activations Density 0.008%

    No Known Activations