© 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
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 134245
    Prev
    Next
    INDEX
    Explanations

    Taiwanese geography and government

    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
    ズル
    0.38
    уд
    0.36
    žem
    0.36
     નક્કી
    0.36
    uves
    0.35
    yno
    0.35
    hren
    0.35
    啶
    0.35
    isbury
    0.35
    ĩ
    0.35
    POSITIVE LOGITS
     Province
    0.57
     province
    0.50
     Provincial
    0.47
     authorities
    0.46
     Provinz
    0.46
     provinces
    0.46
     Authorities
    0.45
     গভর্নর
    0.45
     indígena
    0.45
    Province
    0.44
    Activations Density 0.013%

    No Known Activations