© 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-65K
    7. 51817
    Prev
    Next
    INDEX
    Explanations

    numerical codes for illegal activities

    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_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     zap
    0.46
     ത
    0.43
     RAM
    0.43
    azure
    0.43
    спользу
    0.42
     pivot
    0.42
    EMANN
    0.40
     utwor
    0.40
     []),
    0.40
     опо
    0.39
    POSITIVE LOGITS
     ilegal
    0.54
     سامنا
    0.46
     burglary
    0.46
     robbery
    0.45
     resigning
    0.43
     서비스를
    0.42
     disgraceful
    0.42
     misdemeanor
    0.42
     उनसे
    0.42
     larceny
    0.42
    Activations Density 0.028%

    No Known Activations