© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 41-GEMMASCOPE-2-RES-262K
    7. 25173
    Prev
    Next
    INDEX
    Explanations

    Beijing China PRC

    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_all/layer_41_width_262k_l0_big
    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
    鏻
    0.62
    銠
    0.60
    我們可以
    0.60
    輥
    0.58
    鲽
    0.57
    銨
    0.55
    鱸
    0.55
    閬
    0.55
    齦
    0.54
    鰱
    0.54
    POSITIVE LOGITS
     的
    0.53
     pipa
    0.52
     PRC
    0.50
    ，
    0.50
    的
    0.50
     Beijing
    0.49
     con
    0.49
     Zhang
    0.49
     Tsuen
    0.48
     chopsticks
    0.48
    Activations Density 0.005%

    No Known Activations