© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 13864
    Prev
    Next
    INDEX
    Explanations

    anime and manga

    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_31_width_65k_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
    STERBEDATUM
    0.50
     FORD
    0.49
     रस्सी
    0.47
    
    0.47
     hickory
    0.46
    梭
    0.46
    থর
    0.46
    SMITH
    0.45
    otham
    0.45
    鉚
    0.45
    POSITIVE LOGITS
     anime
    1.55
     Anime
    1.55
    Anime
    1.44
     manga
    1.23
    anime
    1.22
     chibi
    1.05
    动漫
    1.02
     Manga
    1.00
     mangas
    0.93
     kawaii
    0.91
    Activations Density 0.176%

    No Known Activations