© 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-3-1B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 6893
    Prev
    Next
    INDEX
    Explanations

    fundamental laws, principles, and concepts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_22_width_16k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    itory
    0.64
     chromosomes
    0.64
     calific
    0.63
     Roots
    0.61
     membranes
    0.60
     अरुण
    0.59
     suffix
    0.59
     mutated
    0.58
    刺
    0.57
    работ
    0.57
    POSITIVE LOGITS
     Laws
    1.04
     laws
    1.02
    laws
    0.95
     law
    0.95
     Law
    0.94
    结论
    0.93
     leyes
    0.89
    Laws
    0.88
    law
    0.81
    Law
    0.81
    Activations Density 0.176%

    No Known Activations