© 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. 117946
    Prev
    Next
    INDEX
    Explanations

    diluted and suspension concentrations

    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
     intensa
    -0.06
     kondisi
    -0.06
     начинают
    -0.06
    ⚫
    -0.06
    ポスト
    -0.06
    neh
    -0.06
     혼
    -0.06
    питы
    -0.06
    Hãy
    -0.06
     eski
    -0.06
    POSITIVE LOGITS
     يمكن
    0.07
     مثل
    0.06
     defined
    0.06
    पण
    0.06
     so
    0.06
     vậy
    0.06
     delle
    0.06
     ஒருங்கிணை
    0.06
     như
    0.05
     by
    0.05
    Activations Density 0.001%

    No Known Activations