© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 220130
    Prev
    Next
    INDEX
    Explanations

    generally fixate or be

    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_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ሳ
    0.42
     excused
    0.41
    draft
    0.40
    ᓂ
    0.39
     drafted
    0.39
     Draft
    0.38
    outlet
    0.38
     drafting
    0.38
    麗
    0.38
     Бер
    0.38
    POSITIVE LOGITS
    untza
    0.36
    Fruits
    0.36
     Lagrangian
    0.35
     اخر
    0.35
     البي
    0.34
     étudi
    0.34
     simp
    0.34
     caoutch
    0.34
     구조
    0.34
    Radians
    0.34
    Activations Density 0.003%

    No Known Activations