© 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
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 38806
    Prev
    Next
    INDEX
    Explanations

    selected true to multiple options

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

    The neuron predominantly fires on the token “selected,” especially when it’s used in property assignments (e.g. setting a checkbox list item’s Selected value).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    freude
    -0.95
    Undefined
    -0.89
     estreia
    -0.79
    nextPage
    -0.79
     claust
    -0.79
    izado
    -0.78
     ign
    -0.77
     otra
    -0.77
     gifting
    -0.76
    dumps
    -0.75
    POSITIVE LOGITS
    𝒙
    1.38
     already
    1.26
     previously
    1.00
    ighton
    0.91
     partenza
    0.90
     initial
    0.90
     confider
    0.86
    demás
    0.86
    essoal
    0.86
     preexisting
    0.85
    Activations Density 0.003%

    No Known Activations