© 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. 130213
    Prev
    Next
    INDEX
    Explanations

    divisors, factors, multiples, roots

    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
    жета
    0.37
    秉
    0.37
     valor
    0.36
     заяв
    0.36
     шокола
    0.36
     oficialmente
    0.36
     जिस
    0.36
    ികൾ
    0.36
     subchapter
    0.36
    値
    0.36
    POSITIVE LOGITS
    OfString
    0.43
     obtainable
    0.42
     của
    0.42
     of
    0.42
     tồn
    0.40
     खोजने
    0.40
     bagi
    0.40
     ofx
    0.40
     thereof
    0.39
    ของ
    0.38
    Activations Density 0.040%

    No Known Activations