© 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. 70194
    Prev
    Next
    INDEX
    Explanations

    false and misleading statements

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

    This neuron detects legal or formal mentions of making false statements, reports, or lying (e.g., fraud, perjury) in a text.

    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
     imagem
    -0.82
     removeAll
    -0.79
     palavra
    -0.75
    \|^{
    -0.75
    ofy
    -0.72
    醋
    -0.71
     deleteAll
    -0.71
     transfert
    -0.70
     Mantle
    -0.69
     enfant
    -0.69
    POSITIVE LOGITS
     statements
    1.95
     representations
    1.80
     false
    1.72
    representations
    1.66
    false
    1.57
    statements
    1.57
     statement
    1.53
     misleading
    1.51
     Statements
    1.50
     untrue
    1.39
    Activations Density 0.019%

    No Known Activations