© 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. 16949
    Prev
    Next
    INDEX
    Explanations

    conference, symposium, summit, forum

    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
    お子
    0.40
     strain
    0.40
     "/"
    0.40
     دارد
    0.39
     বৈশিষ্ট্য
    0.39
     đã
    0.39
     has
    0.38
     έχει
    0.38
     '/',
    0.37
     wattage
    0.37
    POSITIVE LOGITS
     konfer
    0.77
     conference
    0.75
     conferences
    0.73
     конферен
    0.72
     Symposium
    0.70
     conférence
    0.70
     Forum
    0.69
     конференции
    0.69
     Conference
    0.68
     symposium
    0.66
    Activations Density 0.008%

    No Known Activations