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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 891
    Prev
    Next
    INDEX
    Explanations

    insults and disrespectful language

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

    offensive language

    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_53_width_65k_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
     அதிசய
    0.49
     அதிசயம்
    0.47
     indeterm
    0.46
    indeterminate
    0.41
    釀
    0.41
     indeterminate
    0.41
     puriso
    0.40
     mirac
    0.40
    犧
    0.40
     прио
    0.39
    POSITIVE LOGITS
     insults
    2.22
     insulting
    2.20
     insult
    2.05
     disrespectful
    1.90
     insulted
    1.86
     derogatory
    1.83
     hurtful
    1.77
     ด่า
    1.74
     अपमान
    1.73
     slander
    1.71
    Activations Density 0.560%

    No Known Activations