© 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. 1339
    Prev
    Next
    INDEX
    Explanations

    content that promotes harmful stereotypes and hate speech against marginalized groups.

    oai_token-act-pair · gpt-4o-miniTriggered by @gersonkroiz

    I understand

    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
    this
    0.19
     ardından
    0.19
    ↵
    0.18
     この
    0.16
     کیا۔
    0.16
     tämä
    0.16
     هذا
    0.16
     tomto
    0.16
    。
    0.16
     تاسو
    0.16
    POSITIVE LOGITS
     může
    0.21
     pueden
    0.21
     môže
    0.20
     peut
    0.19
     puede
    0.19
     можуть
    0.19
     certainly
    0.18
     mohou
    0.18
     mogą
    0.18
     może
    0.17
    Activations Density 0.438%

    No Known Activations