© 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. 128531
    Prev
    Next
    INDEX
    Explanations

    sorting or filtering by attribute

    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
    可以是
    -0.06
     särsk
    -0.06
     gegevens
    -0.06
     associé
    -0.06
     شہر
    -0.06
    blah
    -0.06
     тысяч
    -0.06
     manifestation
    -0.06
     圖
    -0.06
     соответству
    -0.06
    POSITIVE LOGITS
     what
    0.07
     then
    0.07
     حسب
    0.06
     his
    0.06
    цене
    0.06
     শেষ
    0.06
    what
    0.06
     also
    0.06
     chronology
    0.06
     coincident
    0.06
    Activations Density 0.025%

    No Known Activations