© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 128748
    Prev
    Next
    INDEX
    Explanations

    The neuron detects technical method and data‐processing terms—words describing the processing, analysis, or reconstruction of scientific data or images.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408

    data processing and analysis

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     while
    -1.11
     when
    -1.09
     sırasında
    -1.08
    genos
    -1.07
    subfigure
    -1.07
     during
    -1.05
     ());
    -1.05
     чрезвы
    -1.02
    鏤
    -1.01
    ocate
    -1.00
    POSITIVE LOGITS
     analysis
    1.60
     vider
    1.26
     analyses
    1.25
     विश्लेषण
    1.23
     tille
    1.22
     PROCESSING
    1.22
     بعد
    1.20
     processing
    1.18
     results
    1.17
     virtuelle
    1.17
    Activations Density 0.129%

    No Known Activations