© 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. 128564
    Prev
    Next
    INDEX
    Explanations

    content from sites

    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
    typically
    -0.06
     would
    -0.06
    directly
    -0.06
     graciously
    -0.06
     humans
    -0.06
     typedef
    -0.06
     ആവശ
    -0.06
    국의
    -0.06
    would
    -0.06
    丁寧に
    -0.06
    POSITIVE LOGITS
     oran
    0.06
    也许
    0.06
    ry
    0.06
    槍
    0.06
     Original
    0.06
    Laundry
    0.06
     authorized
    0.06
     reta
    0.05
     போலீ
    0.05
     suppliers
    0.05
    Activations Density 0.002%

    No Known Activations