© 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. 67009
    Prev
    Next
    INDEX
    Explanations

    whether or not to decide

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

    The neuron fires strongly on function words marking a “whether … or not” decision or choice construction (e.g. “whether,” “or,” “not,” “to …”).

    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
    אין
    -1.08
     megane
    -0.91
    ounced
    -0.88
    EVEN
    -0.87
    vânt
    -0.85
     マー
    -0.84
     خاصی
    -0.83
    agreed
    -0.82
    рии
    -0.81
    dives
    -0.81
    POSITIVE LOGITS
     whether
    3.02
    是否
    2.19
     decide
    2.02
    Whether
    1.99
    whether
    1.95
     Whether
    1.82
     deciding
    1.75
     是否
    1.72
     apakah
    1.57
    要不要
    1.54
    Activations Density 0.093%

    No Known Activations