© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 129953
    Prev
    Next
    INDEX
    Explanations

    ecosystem services and roles

    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
     favorit
    -0.07
     Serum
    -0.06
    μοι
    -0.06
    قتها
    -0.06
     desirous
    -0.06
     preferências
    -0.06
    augmented
    -0.06
     voyages
    -0.06
     prefers
    -0.06
     mandi
    -0.06
    POSITIVE LOGITS
     providing
    0.08
     role
    0.07
     provide
    0.07
    提供
    0.07
    役割
    0.07
    providing
    0.06
    Provide
    0.06
     Providing
    0.06
    帮
    0.06
     valuable
    0.06
    Activations Density 0.060%

    No Known Activations