© 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. 130939
    Prev
    Next
    INDEX
    Explanations

    "at the", "saw the", "track attendance"

    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
    encement
    -0.06
     siehe
    -0.06
    Fin
    -0.06
     CII
    -0.06
     Fin
    -0.06
     longue
    -0.06
     Federer
    -0.05
     右
    -0.05
     кнопку
    -0.05
     satisfacción
    -0.05
    POSITIVE LOGITS
     are
    0.07
    द्रोह
    0.06
     jsou
    0.06
     июля
    0.06
     são
    0.06
     குறை
    0.06
     Cá
    0.06
     ஒப்பந்த
    0.06
     அதிகார
    0.06
     הם
    0.06
    Activations Density 0.001%

    No Known Activations