© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-4-31B
    5. 30-RES-MATRYOSHKA-131K
    7. 131061
    Prev
    Next
    INDEX
    Explanations

    Employee Rights, HPV effect, uncoordinated

    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
     their
    -0.09
     a
    -0.08
    usual
    -0.06
     dlou
    -0.06
     usual
    -0.06
     довго
    -0.06
    但
    -0.06
     ایپلی
    -0.06
    რძ
    -0.06
     但
    -0.06
    POSITIVE LOGITS
     우리가
    0.07
     हमें
    0.06
     আমাদের
    0.06
    私が
    0.06
     madness
    0.06
     cowboy
    0.06
    我們
    0.06
    illä
    0.06
    girlfriend
    0.06
     prepping
    0.06
    Activations Density 0.001%

    No Known Activations