© 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. 129995
    Prev
    Next
    INDEX
    Explanations

    camera viewfinder features

    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
     efforts
    -0.07
     Efforts
    -0.06
    试图
    -0.06
     mumkin
    -0.06
     بر
    -0.06
     ಪ
    -0.06
     путеше
    -0.06
     musical
    -0.06
    ونو
    -0.06
     제작
    -0.06
    POSITIVE LOGITS
    Slave
    0.06
    특히
    0.06
     EVER
    0.06
     wore
    0.05
     ActionBar
    0.05
    모델
    0.05
    AssignableFrom
    0.05
    🥵
    0.05
     models
    0.05
    yss
    0.05
    Activations Density 0.003%

    No Known Activations