© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 56120
    Prev
    Next
    INDEX
    Explanations

    Lie-starting words and names

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

    The neuron activates on occurrences of the letter sequence “Lie” (as in names or the word “Lie”).

    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
     bonbons
    -0.83
    stainless
    -0.82
    breakfast
    -0.81
     getCategory
    -0.81
    CONSULT
    -0.81
     تقديم
    -0.78
    Bim
    -0.77
     zoll
    -0.77
     Insufficient
    -0.77
    teenage
    -0.77
    POSITIVE LOGITS
     detector
    1.16
     Lie
    1.12
    utenants
    1.02
    Lie
    0.97
    Detector
    0.91
    haber
    0.87
     Lipschitz
    0.86
     detection
    0.83
    cama
    0.82
     fallow
    0.82
    Activations Density 0.013%

    No Known Activations