© 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. 118390
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
     жана
    -0.06
     and
    -0.06
     would
    -0.06
    льны
    -0.06
     पहली
    -0.06
    iob
    -0.06
     mellom
    -0.06
     April
    -0.05
     उनके
    -0.05
     तत्कालीन
    -0.05
    POSITIVE LOGITS
     явно
    0.07
     естественно
    0.07
     υπάρχει
    0.06
     Theoretically
    0.06
    untansi
    0.06
     Зараз
    0.06
     противополо
    0.06
     traverses
    0.06
     кстати
    0.06
     rappresent
    0.06
    Activations Density 0.005%

    No Known Activations