© 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. 118561
    Prev
    Next
    INDEX
    Explanations

    Oct, Q, What, Utah, Kate

    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
     способом
    -0.07
    Although
    -0.07
    ٹنگ
    -0.06
    虽然
    -0.06
    イギリス
    -0.06
    渐渐
    -0.06
    England
    -0.06
     কয়েকজন
    -0.06
     Although
    -0.06
    observation
    -0.06
    POSITIVE LOGITS
     Happens
    0.06
    IfExists
    0.06
     наших
    0.06
     naszych
    0.06
     вашего
    0.06
     redir
    0.05
    える
    0.05
    広島
    0.05
    ាយ
    0.05
     tiến
    0.05
    Activations Density 0.008%

    No Known Activations