© 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. 41-GEMMASCOPE-2-RES-262K
    7. 101692
    Prev
    Next
    INDEX
    Explanations

    martial arts, heroes, sects, tea ceremony

    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
     subsystems
    0.47
     multilayer
    0.41
     TED
    0.40
    躾
    0.40
     subsystem
    0.40
    TED
    0.38
    Ca
    0.38
    Greg
    0.38
     предме
    0.37
    ớm
    0.37
    POSITIVE LOGITS
    江湖
    0.91
    丐
    0.71
    侠
    0.68
     sects
    0.64
     chival
    0.63
    俠
    0.62
     Hero
    0.60
    镖
    0.59
     sect
    0.57
    英雄
    0.57
    Activations Density 0.001%

    No Known Activations