© 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. 73605
    Prev
    Next
    INDEX
    Explanations

    works as a profession

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

    This neuron detects occurrences of the word “as” when used in the pattern “as a/an [noun],” typically introducing someone’s role or position.

    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
     they
    -1.91
    titial
    -1.82
     that
    -1.79
    nyata
    -1.78
    celotti
    -1.77
     the
    -1.73
    ꔛ
    -1.73
     gabinete
    -1.73
     放題
    -1.70
    𝄆
    -1.70
    POSITIVE LOGITS
    -
    2.03
     in
    1.99
     =
    1.79
    >
    1.77
     These
    1.65
    D
    1.57
     estos
    1.54
     -
    1.53
     Ã
    1.52
     ine
    1.48
    Activations Density 0.011%

    No Known Activations