© 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. 117479
    Prev
    Next
    INDEX
    Explanations

    followed by description

    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
     Taylor
    -0.06
     визуа
    -0.06
     احتمال
    -0.06
     strangers
    -0.06
     గవర్
    -0.06
    黑暗
    -0.06
     Mustard
    -0.06
    ર્મ
    -0.05
     ENGLISH
    -0.05
     astronaut
    -0.05
    POSITIVE LOGITS
     investigaciones
    0.06
     algunos
    0.06
     algunas
    0.06
     soddisf
    0.06
     satisfacción
    0.06
     რამდენ
    0.06
     ilang
    0.06
     seven
    0.06
     ממ
    0.06
     beberapa
    0.06
    Activations Density 0.004%

    No Known Activations