© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 130881
    Prev
    Next
    INDEX
    Explanations

    FRAX, your reach

    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
     dispar
    -0.06
     ज़र
    -0.06
     callback
    -0.05
    植
    -0.05
    ucian
    -0.05
    ianza
    -0.05
     étab
    -0.05
     across
    -0.05
     défin
    -0.05
    initi
    -0.05
    POSITIVE LOGITS
     சுத்த
    0.06
     প্রকল্পটি
    0.06
     Teraz
    0.06
    調整
    0.06
     sauf
    0.06
    review
    0.06
     Submitted
    0.06
     corp
    0.06
     Except
    0.06
     komple
    0.06
    Activations Density 0.004%

    No Known Activations