© 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. 34-GEMMASCOPE-RES-131K
    7. 32240
    Prev
    Next
    INDEX
    Explanations

    numbers and measurements

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

    The main thing this neuron does is detect numeric tokens conveying quantitative data (e.g. population figures, measurements, percentages).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    ipp
    -0.81
    atam
    -0.77
    vain
    -0.75
     fouling
    -0.75
     σαν
    -0.72
     Rugs
    -0.71
    初期
    -0.69
     wydaje
    -0.67
    °/
    -0.67
    ар
    -0.66
    POSITIVE LOGITS
    viesa
    0.74
    Mediabestanden
    0.74
    worked
    0.72
    quien
    0.71
     mediu
    0.71
    fib
    0.70
    屯
    0.70
     perfume
    0.69
    nih
    0.69
    gnon
    0.69
    Activations Density 0.075%

    No Known Activations