© 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
    2. Gemma-3-27B-IT
    3. 53-GEMMASCOPE-2-RES-262K
    4. 83185
    Prev
    Next
    INDEX
    Explanations

    Taiwanese politics

    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_53_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
    鎚
    0.39
     daß
    0.39
     confess
    0.39
     Mall
    0.39
     cashier
    0.38
     absolute
    0.37
     اي
    0.37
     اهو
    0.37
    塬
    0.37
     успі
    0.37
    POSITIVE LOGITS
     DPP
    0.72
     Legislative
    0.64
    DP
    0.63
     DP
    0.60
    Legisl
    0.59
     legislative
    0.52
    Lai
    0.51
     Tsai
    0.51
    Premier
    0.50
     डीपी
    0.47
    Activations Density 0.008%

    No Known Activations