© 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. 16-GEMMASCOPE-2-RES-65K
    7. 3166
    Prev
    Next
    INDEX
    Explanations

    document creation and submission

    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_16_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
    in
    0.75
    nThe
    0.62
    -;
    0.60
    ン
    0.59
    imize
    0.56
    innt
    0.56
    ként
    0.56
    iség
    0.56
    imetre
    0.54
    ewöhn
    0.54
    POSITIVE LOGITS
    ق
    0.61
     scholarship
    0.58
     From
    0.55
    2
    0.53
    ع
    0.53
    4
    0.52
    وسي
    0.50
     email
    0.50
    អាច
    0.50
     marketing
    0.50
    Activations Density 0.087%

    No Known Activations