© 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-3-12B
    5. 41-GEMMASCOPE-2-RES-65K
    7. 15549
    Prev
    Next
    INDEX
    Explanations

    One Piece

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-12b-pt/resid_post/layer_41_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Израи
    0.60
    ^{*}}{\
    0.60
     অভিনেত্র
    0.59
    asmussen
    0.58
    Israeli
    0.57
    ographiques
    0.56
    🏒
    0.56
    Automation
    0.55
    涔
    0.55
    셩
    0.54
    POSITIVE LOGITS
     Luffy
    1.68
     pirate
    1.25
     pirates
    1.24
     Pirate
    1.23
     Zoro
    1.18
     Pirates
    1.16
     Straw
    1.16
     haki
    1.15
    Straw
    1.11
     straw
    1.08
    Activations Density 0.004%

    No Known Activations