© 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. 31550
    Prev
    Next
    INDEX
    Explanations

    Chinese martial arts and fantasy novels

    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
    檗
    0.50
    ongiorno
    0.40
    Geometric
    0.39
     Geometric
    0.39
     Alphabet
    0.39
    栻
    0.39
     문의
    0.39
     thriving
    0.38
     Ito
    0.38
    鶯
    0.38
    POSITIVE LOGITS
     martial
    0.62
    三国
    0.60
    武
    0.60
    穿越
    0.57
    侠
    0.57
    英雄
    0.57
     fantasy
    0.55
    江湖
    0.54
    小说
    0.54
     hero
    0.54
    Activations Density 0.008%

    No Known Activations