© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 2145
    Prev
    Next
    INDEX
    Explanations

    digital image quantification

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

    This neuron detects quantitative measurement expressions—numbers, units, and metric terms used to report morphometric or other scientific measurements.

    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
    тков
    -0.85
    堇
    -0.85
    DateFormatter
    -0.83
    MapView
    -0.82
     geophysical
    -0.82
    lesssim
    -0.81
    Greenhouse
    -0.79
    Transcrip
    -0.78
     allegory
    -0.78
     annealed
    -0.77
    POSITIVE LOGITS
     software
    1.63
     quantification
    1.59
     quantified
    1.48
     quantitative
    1.38
     Quantification
    1.36
     digital
    1.35
    software
    1.34
     pixel
    1.34
     quantify
    1.34
     measurements
    1.32
    Activations Density 0.224%

    No Known Activations