© 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. 137520
    Prev
    Next
    INDEX
    Explanations

    what it is

    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
    "।
    0.48
    '।
    0.39
    OI
    0.38
     расстоянии
    0.38
     tác
    0.38
     квартиру
    0.37
    RadioButton
    0.37
    чами
    0.37
     الاص
    0.36
    "]},{"
    0.36
    POSITIVE LOGITS
    飨
    0.38
    papers
    0.38
     apertures
    0.37
     ApJ
    0.37
     assumptions
    0.36
     Skyrim
    0.36
     crystalline
    0.36
     kT
    0.35
     ധ
    0.34
    ŋ
    0.34
    Activations Density 0.000%

    No Known Activations