© 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. 116942
    Prev
    Next
    INDEX
    Explanations

    starch processing

    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
    educt
    -0.06
     feminists
    -0.06
    忽略
    -0.06
    ‫
    -0.06
     अभिनेत्री
    -0.06
    柠
    -0.06
    呀
    -0.06
     багато
    -0.06
     لس
    -0.06
     ڈاکٹر
    -0.06
    POSITIVE LOGITS
     Modern
    0.06
    囦
    0.06
     தஞ்ச
    0.06
     manner
    0.06
     ўз
    0.06
    izards
    0.06
    దేశ
    0.06
     deadline
    0.06
     cataract
    0.06
    cattle
    0.06
    Activations Density 0.009%

    No Known Activations