© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 212509
    Prev
    Next
    INDEX
    Explanations

    following punctuation or breaks

    np_acts-logits-general · gemini-2.5-flash-lite

    art generation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    ל
    0.49
    vault
    0.48
    ลด
    0.46
    ดู
    0.45
    大な
    0.44
    วัฒ
    0.43
     그리고
    0.43
     Remarkably
    0.43
    ক
    0.43
     Assim
    0.42
    POSITIVE LOGITS
     té
    0.59
     እንኳ
    0.55
     truyện
    0.54
    的书
    0.53
     titulo
    0.52
    ites
    0.51
    ção
    0.50
     كمان
    0.49
     书
    0.49
    的感觉
    0.48
    Activations Density 0.001%

    No Known Activations