© 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-16K
    7. 8226
    Prev
    Next
    INDEX
    Explanations

    comparison and degree

    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_16k_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
     D
    0.38
     O
    0.38
     expansive
    0.37
     A
    0.37
     compar
    0.37
    =>
    0.37
     unusually
    0.37
     respectivement
    0.37
    <=>
    0.36
    それぞれの
    0.35
    POSITIVE LOGITS
    是我们
    0.55
     있고
    0.48
    那是
    0.47
    是
    0.46
    是一家
    0.43
     adalah
    0.42
    才是
    0.42
     itulah
    0.42
    我都
    0.42
    เป็น
    0.41
    Activations Density 0.155%

    No Known Activations