© 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. 128705
    Prev
    Next
    INDEX
    Explanations

    device or printer

    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
     implement
    -0.06
     реализова
    -0.06
    Didn
    -0.06
     support
    -0.06
    ‍
    -0.06
     Bonn
    -0.06
    പ്പെട്ടി
    -0.06
     atha
    -0.06
     Lehman
    -0.06
    counted
    -0.06
    POSITIVE LOGITS
    選択
    0.08
    选择
    0.07
     voor
    0.07
     selection
    0.07
    toilet
    0.07
     선택
    0.07
     टक
    0.07
     lựa
    0.07
     choix
    0.07
     escoger
    0.06
    Activations Density 0.001%

    No Known Activations