© 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. 220135
    Prev
    Next
    INDEX
    Explanations

    website hero section campaigns

    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
    ‍♂
    0.44
    ‍♀
    0.42
    мости
    0.41
    histor
    0.40
     sifatida
    0.38
    샬
    0.38
     recurrent
    0.38
     retiree
    0.38
    hfill
    0.38
     εμφ
    0.38
    POSITIVE LOGITS
    cursor
    0.45
     cursor
    0.43
     Gucci
    0.43
     gucci
    0.41
    Cursor
    0.40
    쌔
    0.40
     Polyg
    0.39
     grotesque
    0.38
    lemme
    0.38
     sujet
    0.38
    Activations Density 0.009%

    No Known Activations