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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-65K
    4. 1056
    Prev
    Next
    INDEX
    Explanations

    Osaka and Manchester

    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_65k_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
    妫
    0.62
    鵝
    0.56
     Brasília
    0.53
     भूटान
    0.51
     अरुणा
    0.51
    芪
    0.50
     Kenyans
    0.49
    London
    0.48
     उत्तराखंड
    0.48
     Arunachal
    0.48
    POSITIVE LOGITS
     Osaka
    1.17
    大阪
    1.11
     Manchester
    1.05
    Osaka
    1.04
    Manchester
    1.01
     大阪
    1.00
     Lancashire
    0.93
    関西
    0.92
    阪
    0.91
    兵庫
    0.83
    Activations Density 0.021%

    No Known Activations