© 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. 12654
    Prev
    Next
    INDEX
    Explanations

    provocation, aggression, negativity

    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
     проє
    0.45
     কিওয়ার্ড
    0.44
     मुख्‍य
    0.44
     leçon
    0.44
    四个
    0.43
     उन्‍होंने
    0.42
     Ц
    0.42
     उत्तम
    0.42
     ಆಯ್
    0.42
    ⼀
    0.42
    POSITIVE LOGITS
     opiniones
    0.58
     agres
    0.57
     provoc
    0.54
     provocation
    0.50
     insults
    0.50
     aggressive
    0.49
     aggression
    0.49
     agress
    0.49
     abuso
    0.49
     vulgar
    0.48
    Activations Density 0.128%

    No Known Activations