© 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. 120266
    Prev
    Next
    INDEX
    Explanations

    case citations and legal documents

    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
     रखना
    -0.07
     especializado
    -0.06
     aid
    -0.06
     मदद
    -0.06
     नई
    -0.06
     dynamique
    -0.06
     ന
    -0.06
     help
    -0.06
    pecial
    -0.06
     প্রতিক
    -0.06
    POSITIVE LOGITS
     他们
    0.07
    ството
    0.06
     screenshots
    0.06
    λικά
    0.06
     guesswork
    0.06
    Docs
    0.06
     insufficient
    0.06
    就会
    0.06
    Facebook
    0.06
    STAN
    0.06
    Activations Density 0.004%

    No Known Activations