© 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. 129020
    Prev
    Next
    INDEX
    Explanations

    policy or devices

    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
     erstes
    -0.07
     나오고
    -0.06
     aug
    -0.06
     first
    -0.06
    कडून
    -0.06
    ⽤
    -0.06
    Regarding
    -0.06
     στι
    -0.06
    第一个
    -0.06
    แรก
    -0.06
    POSITIVE LOGITS
     town
    0.06
     città
    0.06
     Each
    0.06
     Vicente
    0.06
     pleadings
    0.06
     chaque
    0.06
    NOTE
    0.06
     Anne
    0.06
     towns
    0.06
     Nancy
    0.06
    Activations Density 0.001%

    No Known Activations