© 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. 130518
    Prev
    Next
    INDEX
    Explanations

    biochemistry or biotechnology terms

    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
     konkrét
    -0.07
     거기
    -0.07
     そこ
    -0.07
     szczegól
    -0.07
     poignant
    -0.07
     когда
    -0.07
     зокрема
    -0.07
     اگر
    -0.07
     whether
    -0.07
     материала
    -0.07
    POSITIVE LOGITS
     was
    0.09
     or
    0.08
    或
    0.08
     these
    0.07
     is
    0.07
     atau
    0.07
     或者
    0.06
     или
    0.06
     või
    0.06
     etc
    0.06
    Activations Density 0.067%

    No Known Activations