© 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. 119177
    Prev
    Next
    INDEX
    Explanations

    new standalone VR

    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
    comedy
    -0.07
     Freestyle
    -0.06
     extraordinary
    -0.06
     extraordinarily
    -0.06
     comedy
    -0.06
     ADDITIONAL
    -0.06
     systolic
    -0.06
     straordin
    -0.06
     Nguyen
    -0.06
    🥈
    -0.06
    POSITIVE LOGITS
    avljen
    0.06
     വ്യക്തമാക്കി
    0.06
    概述
    0.06
     giới
    0.06
    child
    0.06
    قیم
    0.06
    Child
    0.06
    esi
    0.06
     clarifies
    0.05
     allies
    0.05
    Activations Density 0.047%

    No Known Activations