© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 13850
    Prev
    Next
    INDEX
    Explanations

    acting or interim followed by a title

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

    The neuron fires on words that mark temporary or provisional officeholders, such as “Acting” or “interim.”

    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
     conlle
    -1.69
     dénon
    -1.63
    苳
    -1.63
    땃
    -1.62
     récomp
    -1.61
     réjou
    -1.57
     rafraî
    -1.57
     SOBRE
    -1.54
    лася
    -1.52
     اولین
    -1.51
    POSITIVE LOGITS
     at
    2.00
     by
    1.94
     on
    1.83
     if
    1.77
    ↵↵
    1.76
     have
    1.66
     or
    1.63
     for
    1.63
     out
    1.59
     trying
    1.58
    Activations Density 0.015%

    No Known Activations