© 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-262K
    7. 201765
    Prev
    Next
    INDEX
    Explanations

    Star Wars legends

    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_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
     koff
    0.45
    fø
    0.43
    δέ
    0.42
    ंब
    0.41
    逵
    0.41
    regs
    0.41
     acusado
    0.41
     for
    0.41
     Ex
    0.40
     общества
    0.40
    POSITIVE LOGITS
    项目的
    0.49
     lining
    0.47
     项目
    0.47
    Ꮶ
    0.46
     abbia
    0.45
     risked
    0.45
    🧞
    0.45
    ™,
    0.45
     countrymen
    0.45
     wersji
    0.44
    Activations Density 0.001%

    No Known Activations