© 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. 117792
    Prev
    Next
    INDEX
    Explanations

    German words, particularly those related to specific items or concepts, often followed by other German words

    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
     كه
    -0.06
     tại
    -0.06
    HEAD
    -0.06
     fungi
    -0.06
     diduga
    -0.06
     alimentaires
    -0.06
     Domin
    -0.06
     জ্ঞান
    -0.06
    !!!!!
    -0.06
     ruler
    -0.06
    POSITIVE LOGITS
     only
    0.07
     seulement
    0.06
     participated
    0.06
     Pembroke
    0.06
     وهذه
    0.06
     فقط
    0.06
    總是
    0.06
    总是
    0.06
    整个
    0.06
    改善
    0.06
    Activations Density 0.009%

    No Known Activations