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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 40544
    Prev
    Next
    INDEX
    Explanations

    social stigma and discrimination

    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_31_width_65k_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
    entropy
    0.38
     entropy
    0.38
     acet
    0.38
    熵
    0.38
    闓
    0.37
     rethinking
    0.37
    ᠠ
    0.37
     こ
    0.37
    允
    0.37
    ewe
    0.37
    POSITIVE LOGITS
     harassment
    0.74
     bullies
    0.73
     persecution
    0.71
     stigmat
    0.70
     bullying
    0.69
     ridicule
    0.66
     bullied
    0.65
     stigma
    0.65
     discriminatory
    0.64
     ostr
    0.63
    Activations Density 0.125%

    No Known Activations