© 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. 117162
    Prev
    Next
    INDEX
    Explanations

    names and affiliations

    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
     частью
    -0.08
     gewisse
    -0.07
     สำหรับ
    -0.07
     ينا
    -0.06
     certaine
    -0.06
    க்கொள்
    -0.06
    🕉
    -0.06
    我們
    -0.06
     whatnot
    -0.06
     annat
    -0.06
    POSITIVE LOGITS
     then
    0.06
    then
    0.06
    会自动
    0.06
    についても
    0.06
     அப்போது
    0.06
    ?(
    0.06
    しており
    0.05
     হিন্দুর
    0.05
    随后
    0.05
    அத
    0.05
    Activations Density 0.004%

    No Known Activations