© 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. 129835
    Prev
    Next
    INDEX
    Explanations

    The neuron is detecting numbers 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
    Img
    -0.06
     deze
    -0.06
    acca
    -0.06
    我觉得
    -0.06
     trabajo
    -0.06
     folgenden
    -0.06
     サ
    -0.06
     प्रवक्ता
    -0.06
     anda
    -0.06
     पालन
    -0.06
    POSITIVE LOGITS
    <|audio>
    0.07
    스는
    0.06
     અથવા
    0.06
    历史上
    0.06
     คือ
    0.06
     riječi
    0.06
     pełni
    0.06
     inaugural
    0.06
     famously
    0.06
     သည်
    0.06
    Activations Density 0.004%

    No Known Activations