© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 25948
    Prev
    Next
    INDEX
    Explanations

    racist stereotypes about men

    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_262k_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
    ီ
    0.42
    न्दु
    0.41
    瑞
    0.40
    শ্বরের
    0.40
     নদীর
    0.39
    Swing
    0.39
    公園
    0.38
    ◹
    0.38
     উদ্বিগ্ন
    0.38
    渦
    0.38
    POSITIVE LOGITS
     nagyon
    0.49
     UAS
    0.46
     IMEI
    0.46
     cytokinin
    0.43
     ശരീ
    0.43
     झाल्यानंतर
    0.43
     puisqu
    0.42
     Differences
    0.42
     freezes
    0.42
     differences
    0.41
    Activations Density 0.002%

    No Known Activations