© 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. 98477
    Prev
    Next
    INDEX
    Explanations

    became eventually

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

    The neuron activates on clause- or sentence-boundary markers—especially commas, periods, and the coordinating conjunction “and.”

    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
    -1.14
     if
    -1.10
    已经
    -1.09
     недавно
    -1.08
     previous
    -1.07
    这么
    -1.07
     miliki
    -1.05
     dekoratif
    -1.05
     previously
    -1.04
    刚刚
    -1.04
    POSITIVE LOGITS
     eventually
    2.55
     became
    2.38
     Eventually
    2.08
     become
    1.93
     soon
    1.84
    Eventually
    1.77
    eventually
    1.67
     then
    1.64
     gradually
    1.54
     Soon
    1.52
    Activations Density 0.045%

    No Known Activations