© 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. 2774
    Prev
    Next
    INDEX
    Explanations

    code blocks and imports

    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
     be
    0.69
     with
    0.60
     datang
    0.59
    (\
    0.57
     awal
    0.57
    uther
    0.56
     dage
    0.56
     o
    0.55
    มีความ
    0.55
     άλλα
    0.55
    POSITIVE LOGITS
    u
    0.72
    g
    0.69
    م
    0.66
    ন
    0.62
    p
    0.61
    و
    0.60
    스
    0.60
    l
    0.59
    k
    0.58
    ل
    0.57
    Activations Density 0.168%

    No Known Activations