© 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-262K
    7. 10781
    Prev
    Next
    INDEX
    Explanations

    unexpected occurrences

    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
    保持
    0.44
    maintain
    0.43
    ಮೀ
    0.43
    烝
    0.41
    দীর
    0.41
    Unsupported
    0.41
    Attempt
    0.40
     devons
    0.40
    懼
    0.39
     항상
    0.39
    POSITIVE LOGITS
     serendip
    0.86
     fortuit
    0.76
     accidentally
    0.74
     accidental
    0.72
     случайно
    0.71
     fateful
    0.71
    偶然
    0.70
     intrigued
    0.69
     tertarik
    0.63
     curiosity
    0.60
    Activations Density 0.095%

    No Known Activations