© 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-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 7694
    Prev
    Next
    INDEX
    Explanations

    fraud, fake, inflated, unauthorized

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    杂
    0.43
     Effective
    0.43
    Effective
    0.43
     Applied
    0.42
     decid
    0.42
     Scary
    0.42
    恻
    0.42
    隐私
    0.41
     Assassin
    0.41
     Becoming
    0.40
    POSITIVE LOGITS
     fraudulently
    1.16
     fraudulent
    1.08
     inflated
    1.08
     illegally
    1.03
     फर्जी
    1.03
     fals
    0.97
     phony
    0.92
     defraud
    0.91
     bogus
    0.90
     fraud
    0.89
    Activations Density 0.213%

    No Known Activations