© 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. 16-GEMMASCOPE-2-RES-262K
    7. 8114
    Prev
    Next
    INDEX
    Explanations

    leave and vacation requests

    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_16_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
     safest
    0.48
     smartest
    0.47
     camera
    0.47
     its
    0.46
    Imagen
    0.46
     t
    0.45
     uner
    0.45
     brightest
    0.44
     one
    0.44
     kill
    0.44
    POSITIVE LOGITS
     अवकाश
    0.62
    idays
    0.61
    ၀၀
    0.57
    休暇
    0.56
     furlough
    0.56
     छुट्टियों
    0.55
     &=\
    0.54
     결방
    0.54
    asadd
    0.54
    льнявыя
    0.53
    Activations Density 0.042%

    No Known Activations