© 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. 41-GEMMASCOPE-2-RES-262K
    7. 63650
    Prev
    Next
    INDEX
    Explanations

    marginal economics

    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_all/layer_41_width_262k_l0_big
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    Bell
    0.40
    Lug
    0.40
    contemporary
    0.39
     வீடு
    0.39
    lg
    0.38
    Columbia
    0.38
    throw
    0.37
    indigo
    0.37
    䅐
    0.37
    埶
    0.37
    POSITIVE LOGITS
     marginal
    1.59
     Marginal
    1.43
    marginal
    1.22
     incremental
    1.11
    Marg
    1.05
     Incre
    0.92
    incremental
    0.90
    Incremental
    0.89
     marg
    0.86
     Marg
    0.84
    Activations Density 0.002%

    No Known Activations