© 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. 116605
    Prev
    Next
    INDEX
    Explanations

    serialization and code construction

    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
    癥
    -0.07
     из
    -0.07
     sowohl
    -0.07
     выпла
    -0.07
    尽可能
    -0.07
    だけでなく
    -0.07
     или
    -0.07
    不僅
    -0.06
     подобные
    -0.06
     подоб
    -0.06
    POSITIVE LOGITS
     other
    0.08
    /
    0.08
    '
    0.06
    最初の
    0.06
     now
    0.06
     Crane
    0.06
     intuition
    0.05
     पहिली
    0.05
     another
    0.05
     first
    0.05
    Activations Density 0.008%

    No Known Activations