© 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. 296
    Prev
    Next
    INDEX
    Explanations

    problems solved

    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
    ряда
    0.40
     chast
    0.40
    acuda
    0.39
     følge
    0.39
    Dish
    0.39
     dish
    0.38
    dish
    0.38
    oro
    0.38
    ்
    0.37
     Zell
    0.36
    POSITIVE LOGITS
     swelled
    0.45
    CurrentByte
    0.43
    Solved
    0.41
     deduced
    0.40
    假的
    0.40
     Position
    0.40
     swollen
    0.39
     solved
    0.38
    astopol
    0.38
    藓
    0.38
    Activations Density 0.000%

    No Known Activations