© 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. 120398
    Prev
    Next
    INDEX
    Explanations

    key[label]

    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
     postdoctoral
    -0.06
     দিনে
    -0.06
     الخام
    -0.06
     Parental
    -0.06
     मिलाकर
    -0.06
     jejich
    -0.06
     clés
    -0.06
    🤚
    -0.06
     parental
    -0.06
     చేశారు
    -0.06
    POSITIVE LOGITS
     ø
    0.06
     inactive
    0.06
    Segoe
    0.06
     renovation
    0.06
    льні
    0.05
    sometimes
    0.05
    Hay
    0.05
     approve
    0.05
    ர்ப
    0.05
     báo
    0.05
    Activations Density 0.017%

    No Known Activations