© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 30167
    Prev
    Next
    INDEX
    Explanations

    introducing lists or groups

    np_acts-logits-general · gemini-2.5-flash-lite

    alkyl groups

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     २
    0.54
     ۲
    0.52
     २५
    0.52
     Biggest
    0.50
     Introductory
    0.49
     Cann
    0.48
     сосредото
    0.48
    ్రహ
    0.48
     २४
    0.48
     ૨
    0.47
    POSITIVE LOGITS
     groups
    0.52
     trusted
    0.51
     trusts
    0.47
     dollars
    0.44
     credible
    0.43
     campaigns
    0.43
    isations
    0.43
     trustworthy
    0.43
     wealthy
    0.42
    ກ
    0.42
    Activations Density 0.001%

    No Known Activations