© 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. 130832
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    我不
    -0.06
     सिनेमा
    -0.06
    ｏ
    -0.06
     आपण
    -0.06
    ｉ
    -0.06
     teníamos
    -0.06
     बिज़नेस
    -0.06
    ህ
    -0.06
    /
    -0.06
    那
    -0.06
    POSITIVE LOGITS
     including
    0.06
     dean
    0.06
     Eine
    0.06
    ပြီး
    0.06
    സ്ലാ
    0.06
     menggunakan
    0.05
    śród
    0.05
    cence
    0.05
    者の
    0.05
     Concurrent
    0.05
    Activations Density 0.000%

    No Known Activations