© 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. 119626
    Prev
    Next
    INDEX
    Explanations

    describing qualities

    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
     ট্রেনিং
    -0.06
     trained
    -0.06
     ;
    -0.06
     bewildered
    -0.06
     establish
    -0.06
     have
    -0.06
    wo
    -0.06
    ;
    -0.06
    を目指
    -0.06
     stressed
    -0.06
    POSITIVE LOGITS
     от
    0.06
    ્રી
    0.06
     ከመ
    0.06
     необы
    0.06
    ⏲
    0.06
     WH
    0.05
     ສຳ
    0.05
     исследования
    0.05
     слегка
    0.05
    forEach
    0.05
    Activations Density 0.032%

    No Known Activations