© 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. 11765
    Prev
    Next
    INDEX
    Explanations

    lying and lies

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    терна
    -0.83
     pazi
    -0.79
     ladrillo
    -0.76
    rante
    -0.75
    avel
    -0.73
     planètes
    -0.72
    Written
    -0.72
    jarse
    -0.72
    efa
    -0.70
     раство
    -0.69
    POSITIVE LOGITS
     lie
    4.63
     lies
    4.53
     lied
    4.38
     lying
    4.03
     liar
    3.73
     Lies
    3.50
     Lie
    3.47
     liars
    3.47
     Lying
    3.34
     LIE
    3.25
    Activations Density 0.108%

    No Known Activations