© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 40-GEMMASCOPE-2-RES-16K
    7. 10910
    Prev
    Next
    INDEX
    Explanations

    toxic exposure and effects

    np_acts-logits-general · gemini-2.5-flash-lite

    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-pt/resid_post/layer_40_width_16k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     جشن
    0.45
    Jazz
    0.45
     الحض
    0.44
    假期
    0.43
    赝
    0.43
     Jazz
    0.42
    崩溃
    0.42
    广播
    0.42
     menjel
    0.41
     Neder
    0.41
    POSITIVE LOGITS
     toxic
    1.95
     toxicity
    1.95
     toxicology
    1.88
     токси
    1.80
    toxic
    1.77
     Toxic
    1.75
     toxicants
    1.72
    毒
    1.72
     Toxicity
    1.69
     Toxicology
    1.68
    Activations Density 0.435%

    No Known Activations