© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 117258
    Prev
    Next
    INDEX
    Explanations

    code snippets

    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
     Ninth
    -0.06
    দের
    -0.06
     ninth
    -0.06
     sixth
    -0.06
    Detailed
    -0.06
     ব্যবসায়ী
    -0.06
     अपराधी
    -0.06
     detailed
    -0.06
     walk
    -0.06
     fifth
    -0.06
    POSITIVE LOGITS
    slightly
    0.07
     向
    0.06
     একজন
    0.06
     各
    0.06
     slightly
    0.06
     слегка
    0.06
    ട്ടിയ
    0.06
     यदि
    0.06
     самым
    0.06
     ي
    0.06
    Activations Density 0.033%

    No Known Activations