© 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. 36686
    Prev
    Next
    INDEX
    Explanations

    according to

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

    This neuron activates on numeric tokens, especially decimal or percentage values.

    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
     then
    -1.52
     затем
    -1.38
     potem
    -1.13
    でしたね
    -1.13
     dann
    -1.12
     THEN
    -1.11
     (
    -1.11
     kemudian
    -1.09
    我们
    -1.09
     потім
    -1.06
    POSITIVE LOGITS
     according
    1.57
     The
    1.49
    According
    1.35
     According
    1.34
     yerde
    1.19
    ätigung
    1.14
     memili
    1.12
     mehreren
    1.11
    They
    1.09
     yesterday
    1.07
    Activations Density 0.073%

    No Known Activations