© 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. 18369
    Prev
    Next
    INDEX
    Explanations

    hate and hatred

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

    prohibiting hate speech

    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
     integrates
    0.52
     observes
    0.50
    明る
    0.50
     pekerja
    0.48
     observing
    0.48
    A
    0.48
     evaporating
    0.47
     deformations
    0.47
    ંને
    0.47
     stresses
    0.47
    POSITIVE LOGITS
     hate
    0.93
     hatred
    0.87
    hate
    0.79
     ненави
    0.78
     hated
    0.78
     نفرت
    0.74
    恨
    0.73
     Hate
    0.71
     hates
    0.70
     dislike
    0.67
    Activations Density 0.018%

    No Known Activations