© 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. 128742
    Prev
    Next
    INDEX
    Explanations

    general * primary care

    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
     Soil
    -0.07
     Andean
    -0.06
     Radical
    -0.06
     закона
    -0.06
     archaic
    -0.06
     Stateful
    -0.06
    🖋
    -0.06
     expressly
    -0.06
     subversive
    -0.06
     reactionary
    -0.06
    POSITIVE LOGITS
    介紹
    0.07
    介绍
    0.06
     שנים
    0.06
     this
    0.06
     পরেই
    0.06
     enorm
    0.06
     apprendre
    0.06
     ş
    0.06
     შემთხვევ
    0.06
    యో
    0.05
    Activations Density 0.009%

    No Known Activations