© 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. 130516
    Prev
    Next
    INDEX
    Explanations

    Q:

    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
    Allison
    -0.06
    averaged
    -0.06
    ҹ
    -0.06
    Bij
    -0.06
     newcomer
    -0.06
    automatically
    -0.06
     precis
    -0.05
     Genet
    -0.05
     Coney
    -0.05
     whaling
    -0.05
    POSITIVE LOGITS
     sturdy
    0.07
     these
    0.07
     postponed
    0.06
     fordi
    0.06
     However
    0.06
     通过
    0.06
     ۴
    0.06
     diseases
    0.06
     هذه
    0.06
     ഈ
    0.06
    Activations Density 0.002%

    No Known Activations