© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31747
    Prev
    Next
    INDEX
    Explanations

    sea-related nouns and locations

    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_40_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
     Things
    0.39
    අ
    0.39
     Aks
    0.38
    Takes
    0.38
     Clo
    0.37
    Clo
    0.37
     ज़
    0.37
    \{
    0.37
    Xiv
    0.37
    \{(
    0.37
    POSITIVE LOGITS
     steamers
    0.54
     ashore
    0.52
     ferries
    0.49
     البحر
    0.49
     offshore
    0.48
     onshore
    0.48
     warships
    0.48
     tankers
    0.47
     hulls
    0.47
     seabed
    0.46
    Activations Density 0.001%

    No Known Activations