© 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. 130800
    Prev
    Next
    INDEX
    Explanations

    code statements

    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
     Ignoring
    -0.06
     then
    -0.06
     சரியாக
    -0.06
                             
    -0.06
    然后在
    -0.06
     한
    -0.06
    career
    -0.05
     سپس
    -0.05
     Yaman
    -0.05
     crater
    -0.05
    POSITIVE LOGITS
    除此之外
    0.07
     विक्रे
    0.06
     Liberties
    0.06
    লাপ
    0.06
    SOME
    0.06
     Центра
    0.05
    ائيل
    0.05
    ार्थियों
    0.05
     گئی
    0.05
     Suède
    0.05
    Activations Density 0.043%

    No Known Activations