© 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. 116765
    Prev
    Next
    INDEX
    Explanations

    text field or input 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
     bottles
    -0.06
     ಹಾಗೂ
    -0.06
     campaigns
    -0.06
    溶解
    -0.06
    📲
    -0.06
    が表示
    -0.06
     boys
    -0.06
     Yo
    -0.06
     fois
    -0.06
     guys
    -0.06
    POSITIVE LOGITS
     তিনিই
    0.06
     extensively
    0.06
     inaugural
    0.06
     البيان
    0.06
    rokken
    0.06
     стиль
    0.05
    ulio
    0.05
    literally
    0.05
     menambah
    0.05
    aggi
    0.05
    Activations Density 0.054%

    No Known Activations