© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 8515
    Prev
    Next
    INDEX
    Explanations

    temptation, lust, craving

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

    desire and temptation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    빻
    0.48
    唖
    0.44
    惊讶
    0.44
    assurer
    0.43
    orkel
    0.42
    不知道
    0.41
    煊
    0.40
    桿
    0.40
    appreciated
    0.40
    ahren
    0.40
    POSITIVE LOGITS
     temptation
    2.23
     temptations
    2.13
     tempting
    1.92
     tempted
    1.81
     লোভ
    1.79
     Tempt
    1.77
     tempt
    1.75
     craving
    1.59
     cravings
    1.55
    诱
    1.52
    Activations Density 0.657%

    No Known Activations