© 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. 130795
    Prev
    Next
    INDEX
    Explanations

    explaining statements or observations

    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
    我会
    -0.07
     showcased
    -0.06
    却没有
    -0.06
    我已经
    -0.06
     deprive
    -0.06
     bungal
    -0.06
     ましょう
    -0.06
     Haitian
    -0.06
    িতেছি
    -0.06
    regulatory
    -0.06
    POSITIVE LOGITS
     that
    0.07
     recherches
    0.06
     saying
    0.06
     понима
    0.06
     teoría
    0.06
     नारे
    0.06
     artinya
    0.05
    涙
    0.05
     यस
    0.05
     nói
    0.05
    Activations Density 0.026%

    No Known Activations