© 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. 38927
    Prev
    Next
    INDEX
    Explanations

    data frame columns and identifiers

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

    The neuron fires on references to dataframe column names or fields in code (e.g. Date, Stock, Close, Min Temp, Max Temp).

    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
     his
    -1.37
     extraordinary
    -1.24
     two
    -1.22
    :[{
    -1.21
    feito
    -1.21
     with
    -1.18
     wisata
    -1.16
    <{
    -1.16
     extraordinarily
    -1.15
    bouts
    -1.14
    POSITIVE LOGITS
     we
    1.17
    _
    1.13
    indd
    1.11
    過了
    1.11
    akterysty
    1.11
    Entire
    1.10
    变了
    1.10
     Chaque
    1.09
    erobic
    1.09
     &
    1.06
    Activations Density 0.040%

    No Known Activations