© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 4955
    Prev
    Next
    INDEX
    Explanations

    list formatting features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     событий
    1.97
    ungannya
    1.90
     czasu
    1.83
    ناة
    1.81
    コツ
    1.78
    etzungen
    1.77
    ovanie
    1.75
    leyici
    1.75
    烛
    1.74
    ovať
    1.72
    POSITIVE LOGITS
     lith
    1.54
     protons
    1.52
     unisex
    1.42
     finite
    1.38
    born
    1.35
     actuation
    1.34
     absorb
    1.33
     dormant
    1.32
     obey
    1.32
    rones
    1.32
    Activations Density 0.009%

    No Known Activations