© 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. 128161
    Prev
    Next
    INDEX
    Explanations

    appearance of something new

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

    The neuron is primarily detecting occurrences of the word “appearance” (especially in the phrase “appearance of”).

    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
    圌
    -2.06
    橚
    -2.03
    nbsp
    -1.89
     cinque
    -1.85
    ícias
    -1.80
    mrow
    -1.80
    ными
    -1.80
     ۱۱
    -1.73
    WICH
    -1.73
     ۷
    -1.73
    POSITIVE LOGITS
     in
    2.94
     Perhaps
    1.89
     new
    1.84
     With
    1.80
     Seems
    1.80
     dětí
    1.77
     Considering
    1.77
     Apparently
    1.76
     Providing
    1.76
     during
    1.75
    Activations Density 0.044%

    No Known Activations