© 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. 130586
    Prev
    Next
    INDEX
    Explanations

    pointers to additional info

    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
     will
    -0.07
     hermoso
    -0.06
     स्टाइलिश
    -0.06
     गरजे
    -0.06
     sensi
    -0.06
     elegantes
    -0.06
    べて
    -0.06
    separate
    -0.06
    SCALE
    -0.06
    stated
    -0.05
    POSITIVE LOGITS
     tentang
    0.07
     insight
    0.06
     từ
    0.06
     unclear
    0.06
     dubious
    0.06
    จาก
    0.06
     insights
    0.06
     עבור
    0.06
     mengenai
    0.06
     Where
    0.06
    Activations Density 0.011%

    No Known Activations