© 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. 34-GEMMASCOPE-RES-131K
    7. 86918
    Prev
    Next
    INDEX
    Explanations

    leading up to

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

    The neuron detects words that mark a temporal buildup before an event (e.g. “leading up to,” “build-up,” 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_34/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
    を持っている
    -0.85
    alism
    -0.80
    Completed
    -0.76
     приви
    -0.76
     Даль
    -0.76
    μο
    -0.75
    develop
    -0.73
     доволь
    -0.72
    oderma
    -0.72
    lieben
    -0.72
    POSITIVE LOGITS
     up
    2.69
     upto
    2.09
    upto
    1.73
     jusqu
    1.33
     buildup
    1.33
     até
    1.25
     run
    1.18
     build
    1.14
     až
    1.13
     approach
    1.12
    Activations Density 0.020%

    No Known Activations