Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 2447
    Prev
    Next
    INDEX
    Explanations

    Thai places and travel

    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
    鳕
    0.71
    纽约
    0.68
     নিউইয়
    0.68
    加拿大
    0.65
     कनाडा
    0.63
     न्यूयॉर्क
    0.62
    鳟
    0.62
     美国
    0.61
     canadien
    0.61
    美国
    0.61
    POSITIVE LOGITS
     Thai
    1.72
     Bangkok
    1.70
     Thailand
    1.62
    Thai
    1.54
    Thailand
    1.50
     thailand
    1.45
     Phuket
    1.34
     Pattaya
    1.25
    泰国
    1.23
     thai
    1.22
    Activations Density 0.115%

    No Known Activations