© 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. 40-GEMMASCOPE-2-RES-262K
    7. 1588
    Prev
    Next
    INDEX
    Explanations

    isekai and anime tropes

    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
    黢
    0.52
    槳
    0.51
    髖
    0.51
    顴
    0.48
    ▾
    0.47
    믄
    0.47
    耔
    0.46
    彝
    0.46
    鉚
    0.45
     constituencies
    0.45
    POSITIVE LOGITS
     anime
    1.03
    Anime
    0.97
     manga
    0.91
     Anime
    0.89
     Naruto
    0.83
     chibi
    0.82
    anime
    0.80
     Goku
    0.78
     Luffy
    0.76
     sakura
    0.73
    Activations Density 0.038%

    No Known Activations