© 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. 130083
    Prev
    Next
    INDEX
    Explanations

    optimization and problem solving

    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
     प्रत्येक
    -0.08
     possèdent
    -0.08
     새로운
    -0.07
     adds
    -0.07
     has
    -0.07
     new
    -0.07
     있
    -0.07
     expensive
    -0.07
     punya
    -0.07
     possui
    -0.07
    POSITIVE LOGITS
    convolution
    0.07
    会议
    0.06
    da
    0.06
     đích
    0.06
     outcome
    0.06
    대에
    0.06
     outcomes
    0.06
     groß
    0.05
    意
    0.05
    ↵
    0.05
    Activations Density 0.003%

    No Known Activations