© 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. 117302
    Prev
    Next
    INDEX
    Explanations

    Government and official entities

    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
    了承
    -0.06
     kunnen
    -0.06
     Many
    -0.06
     zouden
    -0.06
     ряд
    -0.06
     schop
    -0.06
     получили
    -0.06
     ভিতর
    -0.06
    很多
    -0.06
     आश्चर्य
    -0.06
    POSITIVE LOGITS
     new
    0.07
     landmarks
    0.06
    RESULTS
    0.06
     jointly
    0.06
     points
    0.06
     foncé
    0.06
     opos
    0.06
     foresight
    0.06
     succinctly
    0.06
    Results
    0.06
    Activations Density 0.002%

    No Known Activations