© 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. 31-GEMMASCOPE-2-RES-16K
    7. 7835
    Prev
    Next
    INDEX
    Explanations

    anime

    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_16k_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
     Audubon
    0.56
    蜢
    0.52
     transatlantic
    0.50
     Ford
    0.50
    STERBEDATUM
    0.50
     न्यूयॉर्क
    0.49
    Ford
    0.49
    禱
    0.49
    يروس
    0.48
    瞽
    0.48
    POSITIVE LOGITS
     anime
    1.55
     Anime
    1.47
    Anime
    1.40
     manga
    1.38
    anime
    1.23
     kawaii
    1.12
     chibi
    1.07
     mangas
    1.05
     일본
    1.02
     Manga
    1.00
    Activations Density 0.403%

    No Known Activations