© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 42769
    Prev
    Next
    INDEX
    Explanations

    China geopolitics and US relations

    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
     শরণ
    0.42
    纹
    0.42
     умень
    0.42
     Scales
    0.42
    酤
    0.41
    Можно
    0.40
    紋
    0.40
     جذر
    0.40
     występ
    0.40
    萫
    0.39
    POSITIVE LOGITS
    TikTok
    0.79
     China
    0.75
    Biden
    0.75
    China
    0.74
     TikTok
    0.73
     Biden
    0.71
     tiktok
    0.70
     चीन
    0.68
    tiktok
    0.68
     Tiktok
    0.65
    Activations Density 0.051%

    No Known Activations