© 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-3-4B-IT
    5. 22-GEMMASCOPE-2-RES-16K
    7. 3175
    Prev
    Next
    INDEX
    Explanations

    creative expression and ideas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-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
     trackers
    0.80
    机票
    0.72
    iquette
    0.72
     tracker
    0.71
    防护
    0.70
    铠
    0.70
     stow
    0.70
    盔
    0.69
     싫
    0.66
    achricht
    0.66
    POSITIVE LOGITS
     creative
    2.76
     creativity
    2.76
     Creativity
    2.64
    Creative
    2.54
     Creative
    2.46
    creative
    2.39
     creatividad
    2.32
     kreativ
    2.22
     creativo
    2.20
     kreatif
    2.11
    Activations Density 0.680%

    No Known Activations