© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10910
    Prev
    Next
    INDEX
    Explanations

    toxic waste

    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
    Not in Any Lists

    No Comments

    Negative Logits
     выполняется
    0.50
     выполнять
    0.45
     подходит
    0.43
    🍦
    0.43
    Tabs
    0.41
    ยี
    0.41
     সৃ
    0.41
     выполнить
    0.41
     الحض
    0.41
     Boardwalk
    0.40
    POSITIVE LOGITS
     toxicity
    2.13
     toxic
    2.08
     toxicology
    1.94
    毒
    1.91
     токси
    1.89
    toxic
    1.86
     Toxicity
    1.81
     Toxic
    1.80
    toxicity
    1.77
     poisoning
    1.77
    Activations Density 0.224%

    No Known Activations