© 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. 130237
    Prev
    Next
    INDEX
    Explanations

    both parts , lead

    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
    spell
    -0.06
     Eccles
    -0.06
     শ্রম
    -0.05
     ব্লগার
    -0.05
    未能
    -0.05
    ਾਨੂੰ
    -0.05
     역사
    -0.05
    常见的
    -0.05
     pouch
    -0.05
     spell
    -0.05
    POSITIVE LOGITS
    你说
    0.06
     legit
    0.06
     Использу
    0.06
     hagan
    0.06
    彼此
    0.06
     lebih
    0.06
     eivät
    0.06
     dáv
    0.06
     hipótesis
    0.06
    ប្រ
    0.06
    Activations Density 0.047%

    No Known Activations