© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 12313
    Prev
    Next
    INDEX
    Explanations

    Greece, Greek language, 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
     shouldUse
    0.52
    ខ្ញ
    0.51
    듑
    0.48
    ल्लाला
    0.48
    ))%>%
    0.47
    웡
    0.46
     वर्कशीट
    0.46
     టిప్పు
    0.46
    큥
    0.46
     الأمريكي
    0.46
    POSITIVE LOGITS
     Greek
    1.81
     Greece
    1.77
    Greek
    1.63
     Thessaloniki
    1.59
    Greece
    1.55
     Α
    1.54
     greek
    1.53
     griech
    1.51
     Ε
    1.48
     Hellen
    1.46
    Activations Density 0.021%

    No Known Activations