© 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. 129717
    Prev
    Next
    INDEX
    Explanations

    try again later

    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
     åter
    -0.07
     revisiting
    -0.07
     discussions
    -0.07
     revisit
    -0.07
    után
    -0.06
    再び
    -0.06
     invading
    -0.06
     terug
    -0.06
    Builder
    -0.06
     też
    -0.06
    POSITIVE LOGITS
    cope
    0.06
     Specials
    0.06
     misunderstood
    0.06
     ဒီ
    0.05
     slowed
    0.05
     ngươi
    0.05
    ••
    0.05
    ;;
    0.05
     talento
    0.05
     seni
    0.05
    Activations Density 0.007%

    No Known Activations