© 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. 130680
    Prev
    Next
    INDEX
    Explanations

    past conditional or past perfect verbs

    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
     would
    -0.08
    would
    -0.07
     കാരണം
    -0.06
     జీవిత
    -0.06
     because
    -0.06
    performance
    -0.06
     propose
    -0.06
     sarebbe
    -0.06
     subjecting
    -0.06
     cherche
    -0.06
    POSITIVE LOGITS
    blica
    0.07
    不在
    0.07
    ちなみに
    0.06
    喺
    0.06
     små
    0.06
    ことが多い
    0.06
    ങ്ങൾ
    0.06
    并
    0.06
    Tidak
    0.06
     возраста
    0.06
    Activations Density 0.013%

    No Known Activations