© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 11693
    Prev
    Next
    INDEX
    Explanations

    insulting and defamatory content

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

    offensive and insulting 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_31_width_262k_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
     NATURAL
    0.43
    有機
    0.43
    TRANSPORT
    0.43
     контей
    0.42
    捨
    0.41
     партне
    0.41
     gahet
    0.41
     使い
    0.41
     TRANSPORT
    0.40
     गतिशील
    0.40
    POSITIVE LOGITS
     insults
    1.07
     ด่า
    1.05
     defamatory
    1.03
     insulting
    1.02
     slander
    1.00
     insult
    0.96
     defamation
    0.93
    罵
    0.93
    骂
    0.92
     defam
    0.91
    Activations Density 0.132%

    No Known Activations