© 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-262K
    7. 16693
    Prev
    Next
    INDEX
    Explanations

    evergreen

    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_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
    ا
    1.50
    ა
    1.48
    یت
    1.42
    ת
    1.42
    یس
    1.38
    т
    1.37
    اوی
    1.36
    ется
    1.34
    ا۔
    1.32
    اٹ
    1.28
    POSITIVE LOGITS
    0
    1.78
     in
    1.73
    r
    1.55
    h
    1.53
     is
    1.52
     n
    1.45
     t
    1.27
    <0x80>
    1.27
     EVER
    1.25
    (
    1.24
    Activations Density 0.006%

    No Known Activations