© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 34619
    Prev
    Next
    INDEX
    Explanations

    of that year

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron activates on numeric data and associated quantitative expressions (dates, measurements, statistics, percentages) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vuelve
    -0.94
     новая
    -0.90
     memberikan
    -0.88
    álogo
    -0.87
    mayan
    -0.84
     مانند
    -0.81
     山田
    -0.81
     unserer
    -0.81
     batteria
    -0.80
     عندما
    -0.80
    POSITIVE LOGITS
     εκεί
    0.98
     there
    0.98
     thither
    0.94
    該
    0.91
     both
    0.90
     said
    0.87
     various
    0.85
    Bronnen
    0.85
    该
    0.83
     plana
    0.82
    Activations Density 0.179%

    No Known Activations