© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 68359
    Prev
    Next
    INDEX
    Explanations

    monetary values and percentages

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

    This neuron activates on numeric expressions—especially monetary amounts and percentages.

    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
     that
    -1.26
     on
    -1.26
     after
    -1.16
     would
    -1.13
     while
    -1.11
    While
    -1.11
    With
    -1.11
    This
    -1.09
     Belgien
    -1.08
     for
    -1.06
    POSITIVE LOGITS
    3
    1.26
    5
    1.16
    OUGHT
    1.09
     protégé
    1.08
     mettant
    1.08
    elded
    1.07
     EIGHT
    1.06
     boister
    1.06
     magnific
    1.05
    และ
    1.05
    Activations Density 0.010%

    No Known Activations