© 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. 31-GEMMASCOPE-2-RES-262K
    7. 3203
    Prev
    Next
    INDEX
    Explanations

    illegal and harmful 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_31_width_262k_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
    Interpretation
    0.41
    Mamm
    0.41
    Musical
    0.39
    枨
    0.39
     vibes
    0.39
    处理
    0.38
     interpretive
    0.38
     Interpre
    0.38
     Mineral
    0.38
    伫
    0.38
    POSITIVE LOGITS
     illegal
    0.83
     ilegal
    0.83
     illegally
    0.79
     criminals
    0.79
     terrorist
    0.78
     clandestine
    0.76
     clandest
    0.76
     perpetrators
    0.75
     terrorists
    0.75
     unlawfully
    0.71
    Activations Density 0.730%

    No Known Activations