© 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. 119810
    Prev
    Next
    INDEX
    Explanations

    code environments or specific programming syntax

    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
    social
    -0.06
     Love
    -0.06
    Jin
    -0.06
    
    -0.06
     intest
    -0.06
     ~.
    -0.06
     [.
    -0.06
     skirting
    -0.06
     दिश
    -0.06
     четырех
    -0.06
    POSITIVE LOGITS
    ッと
    0.06
     konkuren
    0.06
    വേഷ
    0.06
     department
    0.06
    too
    0.05
     related
    0.05
    opes
    0.05
    立即
    0.05
     प्रभावी
    0.05
     관련된
    0.05
    Activations Density 0.001%

    No Known Activations