© 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. 120354
    Prev
    Next
    INDEX
    Explanations

    navigation elements

    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
    corresponding
    -0.06
     adversity
    -0.06
     advers
    -0.06
    れない
    -0.06
    enderita
    -0.06
     треть
    -0.06
     Нужно
    -0.06
     Praia
    -0.05
     устра
    -0.05
     रोज
    -0.05
    POSITIVE LOGITS
    Hello
    0.06
     विश्वविद्यालयों
    0.06
     shortcuts
    0.06
            
    0.06
     Hello
    0.06
     फिल्मी
    0.06
           
    0.06
     sincer
    0.06
     chile
    0.06
     chic
    0.06
    Activations Density 0.002%

    No Known Activations