© 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. 119356
    Prev
    Next
    INDEX
    Explanations

    client-go libraries

    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
     unload
    -0.07
     protože
    -0.06
     მათი
    -0.06
     على
    -0.06
     আমরা
    -0.06
     उनकी
    -0.06
     service
    -0.06
     አገልግሎ
    -0.06
     خدمات
    -0.06
     services
    -0.06
    POSITIVE LOGITS
    主要
    0.06
     essential
    0.06
     الغذ
    0.05
     벽
    0.05
    workspace
    0.05
     peint
    0.05
     آیا
    0.05
     debate
    0.05
     пище
    0.05
    リビング
    0.05
    Activations Density 0.001%

    No Known Activations