© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 83083
    Prev
    Next
    INDEX
    Explanations

    fair share

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

    This neuron responds to occurrences of the words “fair” and “share,” i.e. mentions of fairness or sharing.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     Bailey
    -0.71
    着了
    -0.68
    ミル
    -0.68
    ért
    -0.67
     spirito
    -0.67
    вається
    -0.66
    وجد
    -0.65
     равно
    -0.64
    primaryStage
    -0.64
    manta
    -0.63
    POSITIVE LOGITS
     share
    6.22
     Share
    5.13
    share
    5.06
    Share
    4.97
     shares
    3.98
     SHARE
    3.78
    SHARE
    3.72
     Shares
    2.92
     sharing
    2.91
    shares
    2.91
    Activations Density 0.077%

    No Known Activations