© 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. 118810
    Prev
    Next
    INDEX
    Explanations

    Madonna and Child

    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
     Detta
    -0.06
    धानी
    -0.06
     definite
    -0.06
    Kenny
    -0.05
    ථා
    -0.05
     తిరిగి
    -0.05
    pra
    -0.05
     lay
    -0.05
     sebaik
    -0.05
    पहली
    -0.05
    POSITIVE LOGITS
     jeszcze
    0.06
     chatbot
    0.06
     ५
    0.06
     static
    0.06
     routinely
    0.06
     przygot
    0.06
     globals
    0.06
     perpetually
    0.06
     noch
    0.06
     chatbots
    0.06
    Activations Density 0.004%

    No Known Activations