© 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. 118990
    Prev
    Next
    INDEX
    Explanations

    section number identifiers

    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
     не
    -0.08
     при
    -0.07
     без
    -0.07
    することが
    -0.07
     так
    -0.07
     За
    -0.07
     У
    -0.07
    を
    -0.06
    销量
    -0.06
     По
    -0.06
    POSITIVE LOGITS
     通过
    0.07
     deze
    0.07
     esta
    0.07
     这个
    0.07
     ఇప్పటికే
    0.06
     هذا
    0.06
    Eventually
    0.06
     ஒவ்வொரு
    0.06
     diese
    0.06
     eventually
    0.06
    Activations Density 0.004%

    No Known Activations