© 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. 10-GEMMASCOPE-RES-131K
    7. 103276
    Prev
    Next
    INDEX
    Explanations

    after certain prepositions

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

    The neuron specifically picks out numeric‐data tokens—especially decimals, percentages, measurement figures, and other statistic‐style numbers in technical or scientific text.

    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
     themselves
    -3.25
     are
    -2.34
     jejich
    -2.19
     their
    -2.16
     Their
    -2.11
     They
    -2.09
     которые
    -2.05
     leurs
    -2.00
     they
    -1.96
     έχουν
    -1.95
    POSITIVE LOGITS
     if
    2.58
     or
    2.42
     itself
    2.14
     one
    2.06
     what
    1.95
     its
    1.80
     it
    1.78
    ichtete
    1.78
     after
    1.77
     is
    1.70
    Activations Density 0.256%

    No Known Activations