© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 14637
    Prev
    Next
    INDEX
    Explanations

    happens to be

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

    The neuron activates strongly on occurrences of the phrase “happen(s) to” (especially “just so happens to”).

    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
     is
    -1.61
    wuchs
    -1.48
    ності
    -1.48
    TabbedPane
    -1.48
    🤑
    -1.48
    llllll
    -1.47
    datable
    -1.45
     eds
    -1.44
     které
    -1.44
     and
    -1.44
    POSITIVE LOGITS
     schlechte
    1.68
     сейчас
    1.65
    すでに
    1.63
    ↵
    1.62
     lends
    1.59
     strengthens
    1.55
     Naturally
    1.52
    既に
    1.52
     nawet
    1.52
     Fortunately
    1.52
    Activations Density 0.009%

    No Known Activations