© 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
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 59651
    Prev
    Next
    INDEX
    Explanations

    Dat prefix and common technical terms

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

    The neuron fires on occurrences of the string “Dat” (i.e. tokens beginning with “Dat,” as in DataGrid, Datomic, Databricks, etc.).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/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
    ’
    -3.53
    selbe
    -2.67
     monumental
    -2.52
     {
    -2.41
     vile
    -2.36
     and
    -2.34
    .,
    -2.33
    ,’
    -2.30
     Might
    -2.27
    \
    -2.27
    POSITIVE LOGITS
    ﮟ
    2.55
    they
    2.44
     KONG
    2.41
     italianos
    2.34
     japoneses
    2.31
    塤
    2.31
     issus
    2.27
     trå
    2.27
    閙
    2.27
    ও
    2.23
    Activations Density 0.010%

    No Known Activations